Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It mentions generating research and lists included aspects, but does not disclose side effects, auth requirements, or output structure. Adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that is front-loaded with the purpose and includes a list of outputs. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, low schema coverage, no output schema, and no annotations, the description lacks guidance on parameter usage, output format, and when to use sibling tools. Insufficient for a complex research tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (output_variable_name has a description). The description does not explain any parameters beyond the topic, leaving research_depth, website_url, and optimization_focus unexplained. Fails to compensate for low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it generates comprehensive AEO & SEO research for a topic, listing inclusions like keyword opportunities and competitor landscape. It distinguishes from siblings like industry_research_generate_research_action by specifying AEO & SEO focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage for AEO & SEO research tasks, but no explicit when-to-use or when-not-to-use guidance. No alternatives are mentioned despite sibling tools with similar names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It does not disclose behavioral traits like input format requirements, side effects, or error conditions. For example, it is unclear what happens if report_data is missing or invalid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 14 words, which is concise and front-loaded. However, the brevity comes at the cost of missing details that could be included without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a render tool, the description lists some contents but lacks workflow context (e.g., it should mention generating research first) and does not describe the output format beyond 'HTML report'. The absence of an output schema places more burden on the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description adds no meaning to the parameters. It does not explain what report_data expects (e.g., a JSON string or variable reference) or the purpose of output_variable_name. The defaults are present but not clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders AEO/SEO research as an HTML report and lists the content (keyword opportunities, citation gaps, recommendations). However, it does not differentiate from sibling tools that also render HTML reports for other domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as the prerequisite aeo_seo_research_generate_research_action. No when-not-to-use or alternative tool names are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose behavioral traits such as side effects (e.g., API calls, data persistence), required permissions, or assumptions about input quality. For a generative tool with 11 parameters, this omission is significant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that lists many components, which is moderately concise but could be better structured (e.g., bullet points) to improve scanability. It is front-loaded with the main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 11 parameters, no output schema, and no annotations, the description is insufficient. It outlines output contents but does not describe how inputs map to outputs, potential limitations, or expected behavior for edge cases (e.g., missing contact_name).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema coverage is only 9% (one parameter described), yet the description adds no parameter-level explanation. Parameter names are self-explanatory, but the description does not clarify format, defaults, or relationships (e.g., how pain_points interacts with objection playbook).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a 'structured Call Game Plan' and enumerates 8 specific components (e.g., pre-call intel, opening approach, objection playbook). It uses a specific verb ('Generates') and resource, and distinguishes itself from sibling tools (no other call game plan tool exists).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like outreach_drafter or meeting_prep. The description implies cold call preparation but does not specify contexts, prerequisites, or situations to avoid.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'gather' without detailing what is returned (e.g., revenue, EPS), whether the operation is read-only, or if there are rate limits or other constraints. This lack of behavioral context reduces transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and front-loaded. It contains no redundant words. However, it could be slightly more informative without sacrificing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of an output schema, the description should explain what kind of earnings information is returned (e.g., revenue, earnings per share). It does not, making it incomplete for an agent to fully understand the tool's output. The three parameters are well-covered by the schema, but the return value is opaque.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with clear descriptions for all three parameters (company, quarter, year). The description adds no new meaning beyond summarizing the timeframe ('by quarter and year'). Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool gathers earnings information for public companies by quarter and year. It uses a specific verb ('gather') and resource ('earnings information'), and differentiates from siblings like 'company_financial_profile' which likely provides broader financial data. However, it doesn't explicitly distinguish itself from all siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'company_financial_profile'. The description implies it is for earnings by quarter/year but does not state exclusions or prerequisites (e.g., requiring a public company ticker).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so description carries full burden. It only states retrieval of information without disclosing data freshness, limitations, or any side effects. Minimal behavioral insight beyond basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with action verb 'Retrieve', efficient and to the point. No redundancy, but could benefit from more structured listing of outputs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description provides only examples of returned fields (market cap, stock price), not a full specification. Leaves ambiguity about what 'detailed' encompasses. Adequate for a simple tool but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with description of 'company' parameter. Description adds examples of returned data (market cap, stock price) but does not significantly enhance meaning beyond schema. Baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it retrieves financial and company profile info for a stock symbol, with examples like market cap and last stock price. However, it does not distinguish itself from sibling tool 'company_financial_info' which likely has similar purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. No conditions or exclusions provided, leaving the agent to infer usage from purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description must disclose behavioral traits but only states 'add or update'. It does not explain behavior when both create_if_missing and update_existing are true, error conditions, or side effects like overwriting data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but too brief for the complexity. It could be restructured to front-load key details, but no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and many sibling tools, the description is incomplete. It does not mention return values (no output schema) or how it integrates with company research. The description leaves significant gaps for an AI agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the parameter descriptions; it does not clarify the relationship between domain and company_id or the purpose of output_variable_name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'add or update' and the resource 'company in HubSpot CRM', distinguishing it from read-only HubSpot tools like get_hubspot_company_object. However, it does not specify whether it syncs research data, leaving some ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like hubspot.v2.create_object or update_object. Missing prerequisites such as HubSpot integration requirements or permission needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must fully disclose behavior. It mentions 'cached data' but the parameter 'use_live_data' (default true) suggests live web search is included, creating ambiguity. No disclosure of side effects, permissions, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, efficiently communicating the core purpose without extraneous words. It is appropriately front-loaded and concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having 4 parameters and no output schema, the description fails to explain key aspects like output format, interaction between cached and live data, or prerequisites. The agent lacks sufficient context for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter having a basic description. The tool description adds minimal extra meaning (e.g., 'cached data'), but the default behavior of use_live_data contradicts this. Overall, the schema already provides adequate semantic information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: answering custom research questions about a company using cached data and LLM. It effectively distinguishes from siblings like get_section or get_report by focusing on custom questions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like ask_domain_question or get_section. The description does not mention exclusions or preferred contexts, leaving the agent without decision criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must disclose behavior. It mentions caching per user/domain, which is helpful. However, it does not describe authentication needs, rate limits, data staleness, or the effect of parameters like use_live_search on behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences. The first sentence states the core purpose, and the second adds a key behavioral detail (caching). No redundant or unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema, the description does not explain the format or structure of the answer. It also omits details on caching behavior implications (e.g., how to force refresh). While it covers basic usage, it leaves gaps for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the description adds no additional parameter meaning. It does not explain the difference between use_report_context and use_live_search, nor the role of output_variable_name beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Ask a custom research question') and the resource ('about a company domain'). It adds a distinguishing feature (caching per user/domain). However, it does not explicitly differentiate from the very similar sibling tool 'company_research_v2_answer_question', which could cause confusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no context on its appropriate use cases. It only states what it does, not when or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Says 'get' implying read-only but does not explicitly state no side effects, pagination behavior, or data source constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundant words, front-loaded with key action. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Description tells purpose but lacks details on return structure, ordering, or limitations (e.g., only returns questions asked via the tool). Adequate for a simple retrieval tool but could be improved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with clear parameter descriptions. Tool description adds no additional semantic value beyond the schema, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb (get), resource (Q&A for a domain), and scope (user's history). Distinguishes from sibling tools like 'ask_domain_question' and 'answer_question' which perform actions rather than retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., ask a new question vs. view history). Agent must infer usage context from the description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden for behavioral disclosure. It implies a read-only operation ('Get'), but does not explicitly state it is non-destructive, requires no special permissions, or what happens if the report is incomplete. Significant gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no filler. It is appropriately front-loaded for a simple retrieval tool, though it could benefit from a second sentence to elaborate on return value or prerequisites.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and 3 parameters, the description is too minimal. It does not explain what constitutes a 'completed' report, the response structure, or how optional HTML is generated. Sibling tools provide some context, but the description itself is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (all 3 parameters described in the schema). The description adds only the phrase 'with all sections and optional HTML content', which loosely maps to include_html but does not provide meaning beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Get' and clearly identifies the resource as a 'completed research report with all sections', which distinguishes it from siblings like company_research_v2_get_section (single section) and company_research_v2_render_html (HTML only).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. For instance, it does not mention that get_section is for a single section, or that get_status is for checking progress. The description offers no exclusion criteria or context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. However, it only states the basic action without indicating side effects (likely none), authorization needs, or read-only nature. This is insufficient for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no redundant words. However, it is so concise that it omits potentially useful information, yet it remains efficient for its purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 3 parameters, an enum, and no output schema, the description is too minimal. It fails to hint at the available sections (though schema lists them), what the returned data looks like, or prerequisites (e.g., a report must be researched first).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all parameters, so the baseline is 3. The description adds no additional meaning beyond the schema, such as explaining the role of output_variable_name or the purpose of each section key.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get a specific section from a research report' clearly states the action (get) and the resource (section of a report). It distinguishes itself from sibling tools like get_report (full report) and get_status (status).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lacks any guidance on when to use this tool versus alternatives. For example, it does not mention that for a full report, one should use get_report, or that this tool is for retrieving individual sections after a report is generated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so description must carry full burden. It only says 'poll' (implying non-destructive read) and mentions checking 'is_complete', but does not disclose behavior on invalid report_id, rate limits, or potential errors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states purpose, second gives usage. No unnecessary words, well front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists. Description hints at is_complete boolean in response, but does not mention other potential fields like progress percentage or error states. Adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover both parameters with 100% coverage. Description adds context about using in a loop and checking is_complete, but does not add significant meaning beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Poll for research report progress' clearly states the verb (poll) and resource (research report progress). It distinguishes from siblings like start_research (initiates) and get_report (retrieves final report).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use in a loop until is_complete is true', providing clear usage pattern. It implies polling context but does not mention alternatives or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It merely states the function without disclosing behavioral traits like pagination, sorting, or behavior when no companies are tracked.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is concise but omits necessary details about filtering parameters and return value. It is appropriately short but lacks completeness for effective use.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters, no output schema, and no annotations, the description is too brief. It fails to explain filtering options or output format, leaving agents uncertain about usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with well-described parameters. The description adds no additional meaning beyond the schema, resulting in baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves all companies tracked by the user, distinguishing it from sibling tools like search_companies which finds new companies. However, it does not explicitly differentiate itself from similar list operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like company_research_v2_search_companies or company_research_v2_track_company. The context is implied but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It states the tool outputs 'professional, mobile-friendly HTML' and includes links and sections, which gives some insight into the output. However, it does not disclose behavior regarding parameter conflicts, performance, error handling, or how the HTML is returned (e.g., stored in variable). Basic transparency is present but lacks detail.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with two sentences: the first states the core purpose, the second adds key features. It is front-loaded and avoids fluff. However, it could be slightly more informative without becoming verbose, hence a 4 rather than 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a render tool with 3 parameters, no output schema, and no nested objects, the description provides basic purpose and features. However, it lacks guidance on parameter interaction (e.g., what happens if both `report_data` and `report_id` are provided) and does not explicitly state that the output is the HTML string stored in the variable. Slightly incomplete for full contextual understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description does not add meaning beyond the schema; it only mentions features of the report output, not parameter usage. The parameter descriptions in the schema already explain purpose, so the description provides no additional semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a complete company research report as HTML, uses a specific verb ('Render') and resource ('company research report'), and adds detail about including links to article sources and all research sections. Among sibling tools, it is distinct from other render tools by its focus on company research and mention of sources and sections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like `company_research_v2_get_report` or other render tools. It does not specify prerequisites (e.g., having run full research first) or when not to use it. The parameter description for `report_data` hints at a prerequisite, but the tool-level description lacks such context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It only states the tool returns a JSON report. It omits whether the research is long-running, uses external APIs, requires cache, or has rate limits. The 'force_refresh' parameter hints at caching but is not explained in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with action and output. No waste. However, it could be more informative while remaining concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 19 parameters, no output schema, and no annotations. The description is too sparse to provide complete context about the research flow, synchronous vs asynchronous behavior, or how to interpret the JSON. Sibling tools indicate a rich ecosystem, but this description fails to connect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds no value beyond the schema; 'configurable sections' merely echoes the boolean flags. The parameter descriptions in schema are adequate, so the description's contribution is minimal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Run' and resource 'comprehensive company research' with configurable sections and return of JSON report. While it distinguishes from siblings like 'start_research' by implying full execution, it doesn't explicitly differentiate from 'get_report' or 'answer_question'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. No prerequisites, no warnings about cost or time, no exclusions. The description does not help the agent decide when to choose this tool over others like 'company_research_v2_start_research'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description adds 'Extracts filters' implying parsing behavior but no details on safety, rate limits, or side effects. Adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Very short single sentence, no wasted words. Could benefit from slight expansion for clarity, but appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and description omits return format (e.g., company fields, pagination details). Without this, agent cannot effectively use results. Among sibling tools, lacks relational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage 100% so baseline 3. Description adds minimal extra meaning beyond schema (only mentions filter extraction for query parameter). No additional semantics for page, page_size, or output_variable_name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States 'Search for companies using natural language query' with specific verb and resource. Mentions filter extraction, differentiating from generic search tools, but doesn't explicitly distinguish from sibling company research search tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives like `company_research_v2_run_full_research` or `get_search_results`. Lacks context for tool selection among many siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It fails to explain whether the research is synchronous/asynchronous, cache behavior (despite a 'force_refresh' parameter), error conditions, or side effects (e.g., overwriting previous reports).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at 13 words across two sentences, immediately stating the action and key output. Every word earns its place with no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite its conciseness, the description lacks completeness given the tool's role in a multi-step research workflow. It does not explain the research process, how to use the report_id, or confirm the polling pattern implied by 'for polling status,' leaving gaps for an AI agent unfamiliar with the sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All parameters are fully described in the input schema (100% coverage), so the description adds no additional meaning beyond the schema. The baseline of 3 applies as the description does not enhance understanding of the parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Start researching a company by domain' and specifies the key return value 'Returns report_id for polling status,' which distinguishes it from related tools like 'get_report' or 'get_status' that handle completed results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (to initiate research) and hints at a follow-up polling pattern via 'report_id for polling status,' but it does not explicitly state when not to use this tool or mention alternatives among the many similar research tools in the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It implies a mutation but fails to specify side effects (e.g., what happens if the company is already tracked, whether it overrides existing data, or auth requirements). No mention of rate limits or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, which is front-loaded. However, it is too brief and could include more useful information without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (5 parameters, no output schema, no annotations), the description is incomplete. It does not explain the return value (despite the 'output_variable_name' parameter), error handling, or persistence behavior. A tracking tool should clarify these aspects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already describes each parameter. The description adds no additional meaning beyond the schema; for example, it doesn't clarify how to choose between 'domain' and 'company_id' or the expected format of 'tags'. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add a company'), the resource ('to the user's tracked list'), and the purpose ('for monitoring'). It effectively distinguishes from the sibling tool 'company_research_v2_list_tracked' which lists tracked companies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives (e.g., list_tracked for viewing, a hypothetical remove tool). It does not mention prerequisites, such as whether the company must already exist in the system, or conditions like duplicate handling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It only describes the rendering action without disclosing side effects, permissions, or limitations. As a pure rendering operation, it is likely non-destructive, but this is not stated. The description lacks sufficient transparency for an agent to infer safety or constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary purpose. Every word adds value, with no extraneous information. It is concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (two parameters, no output schema), the description adequately covers purpose and input. It lacks details on the output format or error handling, but for a rendering tool of moderate complexity, it is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed parameter descriptions (e.g., brief_data instructs to use {{competitive_brief}}). The tool description adds little beyond reinforcing the input source, so it meets the baseline but does not enhance understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a competitive brief as HTML, specifying the input from 'CBFull Run Full Competitive Brief'. It effectively communicates the core purpose but doesn't explicitly differentiate it from other render tools in the sibling list, though its specific input requirement provides implicit distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the prerequisite input ('output from [CBFull] Run Full Competitive Brief'), guiding the agent to use this tool after running that specific action. However, it does not provide when-not-to-use guidance or mention alternatives, which are not critical given the clear dependency.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must disclose behaviors. It only mentions generating a brief and returning JSON, without covering caching, data sources, auth, processing duration, or side effects. The presence of a force_refresh parameter hints at caching but is not explained in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise. However, given the tool has 14 parameters, the description could benefit from slightly more context without becoming verbose. It is front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 14 parameters, no output schema, and many sibling tools. The description does not explain what constitutes a 'full brief,' how the output JSON is structured, or how this tool differs from similar research tools. It is insufficient for an agent to fully understand its capabilities.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters. The tool description adds no extra meaning beyond stating it generates a full brief. Baseline 3 is appropriate as description does not degrade but adds minimal value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a comprehensive competitive intelligence brief with all sections and returns full JSON output. The verb 'generate' and resource 'competitive intelligence brief' are specific, and it distinguishes from siblings like competitive_brief_render_brief_html.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The sibling list includes many research tools, but the description offers no context about when this specific tool is preferred, such as for generating a complete brief vs. other partial research tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It uses marketing language ('uncover', 'discover', 'synthesized') without disclosing data sources, side effects, or limitations. Does not clarify what actions it performs (e.g., reads emails, scrapes LinkedIn).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but overly vague. It front-loads action verbs but lacks specific detail. Every word feels generic rather than earning its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, multiple boolean toggles, no output schema), the description is insufficient. It does not explain output format, interaction between flags, or prerequisites. The description is too incomplete for an agent to reliably use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with good descriptions, enums, and defaults. The tool description adds no additional meaning beyond the high-level purpose; it does not elaborate on how parameters relate or should be combined.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it generates synthesized intelligence for meetings/deal prep, but it is vague and does not clearly differentiate from sibling tools like 'enrich_person', 'contact_research', or 'meeting_prep_*' tools. Lacks a specific verb-resource pair.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. No when-not-to-use or exclusions provided. Among many similar tools, this omission reduces clarity for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions using specific search engines and generating conversation intelligence, but does not disclose limitations (e.g., contact not found), rate limits, or whether the tool modifies data. The description implies a read-only research operation but lacks explicit safety cues.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with primary purpose, then details on methods and outputs. Every sentence adds value without redundancy. Very efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and no output schema, the description covers the tool's purpose and outputs adequately. However, it lacks information on error handling, success criteria, and limitations (e.g., required email format for enrichment). For a research tool generating conversation intelligence, more details on output structure or reliability could improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description does not add significant meaning beyond schema for each parameter, but the overall context of researching and enriching contacts helps understand parameter usage. No additional parameter details are provided in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool researches contacts using Perplexity Sonar Pro and deep web search, with specific outputs like profile enrichment and conversation intelligence. It distinguishes from sibling tools like enrich_person (basic enrichment) and get_person_object (simple retrieval) through its multi-source triangulation and conversation prep focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like enrich_person, prospect_research, or meeting_prep_* tools. The description implies use for deep research and conversation prep, but doesn't specify exclusions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must bear the burden. It correctly indicates the tool performs a crawl (implying external network access) and generates a structured audit. However, it does not disclose potential side effects (e.g., rate limits, site impact), required authentication, or time cost. The description is moderately transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence front-loaded with the verb 'crawls'. It lists key outputs without redundancy. Every element adds value, and no unnecessary words exist.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description outlines expected deliverables (scores, action plan, gap analysis, etc.), giving the agent a good idea of the result. However, it lacks details on parameter usage, process duration, or return format, leaving gaps in completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (2 of 4 parameters have descriptions in schema). The tool description does not describe individual parameters (e.g., audit_scope, optimization_focus) beyond listing output components. It adds no meaning beyond the schema, so the score is below baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Crawls a website') and specifies the outputs ('structured content audit with SEO/AEO scores, prioritized action plan, content gap analysis, keyword cannibalization detection, page-level inventory'). This distinguishes it from sibling tools like content_audit_render_audit_report, which handles rendering rather than generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives (e.g., content_audit_render_audit_report for rendering or other content tools). It lacks 'when-to-use' or 'when-not-to-use' guidance, leaving the agent to infer usage from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries burden. It mentions output format but omits behavioral details like side effects, required permissions, or input constraints. For a non-trivial render tool, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no redundant words. It delivers core purpose immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the output structure is hinted, key information—parameter usage, input expectations, output details beyond the listed sections—is missing. Given no schema descriptions and no output schema, the description should compensate but does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain the two parameters (report_data, output_variable_name) or their expected formats. Default values offer minimal clues, but no meaningful guidance is added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a content audit as an HTML report with specific sections (site health dashboard, findings, page inventory). It uses a specific verb ('renders') and resource ('content audit'), effectively distinguishing it from sibling tools like content_audit_generate_audit_action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context—rendering an already-generated audit—but does not explicitly state when to use this tool versus alternatives (e.g., other render reports) or exclude cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the output components (SEO metadata, linking suggestions, etc.) but does not mention behavioral traits like requirements, side effects, or limitations. It is somewhat transparent but lacks depth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and front-loaded with the primary action. It lists key output components without waste. However, it could be slightly more structured with separate clauses.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, no output schema, no annotations), the description is too brief. It does not cover important details like output format, enum meanings, or how parameters affect output. Incomplete for agent decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25%, and the description does not explain any parameters beyond the overall purpose. It fails to compensate for low schema coverage, providing no additional meaning for parameters like topic, target_keyword, content_type, etc.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a complete, publish-ready article with specific components (SEO metadata, linking suggestions, image prompt, checklist). The verb 'generates' and resource 'article' are specific, and it distinguishes from siblings like content_planner and social_post_creator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, context, or when not to use it. It simply describes the output without any usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It only states the output format but fails to mention side effects, state changes, or requirements (e.g., input must be a valid article). This is insufficient for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence (14 words) that front-loads the action. While brief, it lacks structured details that could aid understanding. It earns a 4 for being efficient but not overly terse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given two parameters (one required), no output schema, and no annotations, the description is too sparse. It does not explain input formatting, return structure, or prerequisites, leaving significant gaps for an agent to correctly invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description does not explain the parameters beyond the schema's basic definitions. It mentions the report components but does not map them to 'report_data' or clarify the purpose of 'output_variable_name'. The description adds minimal value over the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (renders), the resource (generated article), and the output (HTML report with specific components like SEO metadata, article body, links, checklist). It is distinct from sibling tools such as 'content_creator_generate_article_action' which focuses on generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It lacks prerequisites (e.g., 'Use after generating an article') or exclusions, and there is no differentiation from other render tools in the sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden. It mentions generating a plan but does not disclose if the tool writes to a database, requires authentication, has rate limits, or any side effects. For a generation tool, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the key output (content calendar) and qualifiers (SEO/AEO, schedule, rationale). No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 parameters, no output schema, and no annotations, the description is too brief. It does not explain how the plan is returned (despite output_variable_name), what the plan includes beyond a calendar, or how parameters interact. The agent lacks sufficient context to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 43%, leaving many parameters without explanations. The description adds minimal value: it hints that 'optimization_focus' relates to SEO/AEO but does not clarify other parameters like planning_period, publishing_capacity, or brand_voice. It fails to compensate for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates a content calendar with article ideas mapped to SEO/AEO opportunities, a publishing schedule, and strategic rationale. This distinguishes it from siblings like content_creator_generate_article_action (single article) and content_audit_generate_audit_action (audit) by specifying the output is a calendar and plan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used for planning a content calendar, but it does not explicitly state when to choose it over alternatives such as content_audit or content_creator. No when-to-use or when-not-to-use guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It states 'renders' which implies a non-destructive output generation, but it doesn't clarify side effects, required inputs (like prior plan generation), or how the report is structured. Basic transparency but insufficient for full understanding.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that efficiently conveys the core purpose without extraneous words. It is front-loaded with the verb and resource, making it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 2 parameters (with 0% schema description) and no output schema or annotations, the description is minimal. It explains the basic purpose but lacks details on data format, prerequisites, expected output structure, and error behavior. An agent would need additional context to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning the schema provides no parameter descriptions. The description does not explain the parameters 'report_data' or 'output_variable_name' beyond what the schema (name and type) already shows. It adds no semantic meaning, so it fails to compensate for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool renders a content calendar as an HTML report with week-by-week content briefs. It uses specific verb 'renders' and resource 'content calendar HTML report', and the detail 'week-by-week' distinguishes it from sibling tools like content_planner_generate_content_plan_action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs. alternatives. The description implies it is for rendering after generation, but it doesn't state prerequisites or when not to use it. Sibling names provide some context, but the description itself lacks usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral disclosure. It only states the conversion action, omitting key details like whether the original file is preserved, if the operation is asynchronous, any size or format limitations, or what the output is (e.g., a URL).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no filler. It efficiently conveys the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema, the description covers the basic purpose but lacks context about output handling, error scenarios, or supported formats beyond the examples. It is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the input schema already provides for the two parameters (input_file and convert_to_extension).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool converts uploaded files to different formats like PDF, TXT, or PNG, which clearly communicates the verb (convert) and resource (files). However, it does not differentiate from similar sibling tools like file_converter_convert_action or convert_file_options, which likely perform the same function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as convert_file_options or other file_converter tools. There are no prerequisites, exclusions, or contextual cues to help an agent decide.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must fully disclose behavior. It only states it 'gets' options, without mentioning network calls, caching, data source, or result structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with action verb. Very concise with no wasted words, though could slightly elaborate on output without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description should at least hint at return format or scope. It omits what the 'options' look like, leaving the agent underinformed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with description 'File extension' for the parameter. The tool description adds no further semantics like format examples or case sensitivity, staying at baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses specific verb 'Gets' and resource 'full set of options that a file extension can be converted to', clearly distinguishing it from convert_file and other file conversion tools that actually perform actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. It does not indicate that this should be called before conversion or describe any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description only states the basic action without disclosing behavioral traits such as file size limits, the fact that it stores the file URL in a variable (output_variable_name), or any side effects. Since no annotations are provided, the description carries full responsibility for transparency, and the minimal text fails to convey important behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no wasted words. It is appropriately concise for a simple tool, though additional context (e.g., what happens after saving) could improve usefulness without sacrificing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 required params, no complex output), the description is largely complete: it identifies the action and result. However, it does not explain the role of 'output_variable_name' (storing the file URL) or mention that the file is downloadable, which is partially covered by the schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add any meaning beyond what the input schema already provides; it merely restates the core purpose without elaborating on how parameters like 'output_variable_name' function in the tool's operation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Save') and resource ('text content as a downloadable file'), clearly indicating the tool creates a file from text. This distinguishes it from siblings like 'convert_file' (which converts existing files) and 'format_text' (which does not produce a download).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., 'convert_file' for converting existing files or 'get_variable_from_database' for retrieving stored data). The description implies usage for saving text as a file but does not provide exclusions or context for when other tools would be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description must communicate behavioral traits. It implies a read-only operation ('Get'), but does not disclose output format, data freshness, or any side effects. It is adequate but minimal for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, 14 words, front-loaded with the core action. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description should clarify what 'detailed metadata' includes. It does not elaborate on return structure (e.g., 'name, description, parameters'). It is minimally complete for a simple getter but lacks specificity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter description already mentions ID or slug. The tool description adds no new semantic meaning beyond confirming that both ID and slug are accepted. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'detailed metadata, input fields, and output fields for a specific agent'. It specifies the identifier method ('by its ID or slug') and the scope ('specific agent'). This clearly distinguishes it from sibling tools like 'invoke_agent' or 'list_agent_memories'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (when you need agent details), but does not mention when not to use it or alternatives (e.g., 'openclaw_get_details' for a different system). No explicit guidance on prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose behavioral traits such as authentication needs, rate limits, or the extent of data retrieved. It only implies a read operation without specifics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with 9 words. It is very concise, but could include more context without sacrificing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of the tool (1 param, no output schema, no annotations), the description is adequate but lacks details about the output format or types of details returned. It is minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (the parameter 'domain' is described in the schema). The description adds no additional meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Gather' and the resource 'domain', specifying it retrieves registrar details. This distinguishes it from sibling tools that focus on company research or social media profiles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. There are sibling tools like 'company_research_v2_ask_domain_question' that could also provide domain info, but the description does not clarify when to choose this one.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so description must carry full burden. It lists what data is fetched (attendees, transcript, AI insights) but does not disclose permissions needed, rate limits, or how data is processed. Parameter booleans imply optional inclusion, but overall behavioral details are minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that front-loads purpose. It is clear and efficient, though could be slightly more concise. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters and no output schema, the description should explain return structure or how to use output_variable_name. It lacks guidance on what the enriched data looks like or how to utilize it, making it incomplete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions. The tool description repeats the parameter list but does not add new meaning beyond schema. Baseline 3 is appropriate; no significant improvement over schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool enriches a calendar event with comprehensive details (attendees, notes, transcript, AI insights) and specifies supported providers (Google/Outlook). This distinguishes it from sibling tools like get_calendar_events_list which only lists events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives (e.g., meeting_followup_analyze_transcript). Usage context is only implied by the mention of 'comprehensive details', but no when-not-to-use or alternative recommendations are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavior. It mentions data sources (Fiber AI, LLM, Perplexity), caching (30 days), and the fields returned. This gives sufficient transparency for an enrichment tool, though rate limits or error behavior are not mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: first states the action and data sources, second lists return fields, caching, and input requirement. No fluff, crucial information front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lists all return fields and mentions caching. No output schema exists, but the returned data is clearly enumerated. It lacks guidance on failure cases or resolution quality, but for a data enrichment tool it is reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that email is the best identifier and that name+company or LinkedIn URL are fallbacks. It also groups inputs into the required 'at least one' condition, which the schema does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool enriches a person's professional profile using Fiber AI, LLM, and Perplexity. It lists specific return fields and distinguishes itself from sibling tools like get_linkedin_profile by combining multiple data sources and naming the enrichment action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the required inputs: 'Provide at least one of: email, name + company, or LinkedIn URL.' This guides the agent on when to use the tool. It does not compare to sibling tools or give when-not-to-use scenarios, but the input requirement is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It mentions 'search' and 'extract' but does not disclose authentication needs, rate limits, or that the tool may require Gmail/Outlook access. The AI analysis aspect is only partially covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no unnecessary words. It front-loads the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having 7 parameters and no output schema, the description fails to mention that results are stored in a variable (via output_variable_name). It does not describe the output format or provide enough context for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The main description adds no additional meaning beyond the schema; the parameter descriptions in the schema are already detailed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Search a contact's email history') and resource ('email history'), with additional objectives like extracting patterns and generating insights. It distinguishes itself from sibling tools, which are not email-specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for finding relevant emails from a contact based on meeting details, but lacks explicit guidance on when to use this over alternatives or when not to use it. No exclusions or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions it uses CloudConvert and supports many formats, but fails to disclose critical behavioral traits such as whether conversion is synchronous or asynchronous, file size limits, authentication requirements, or what happens to the original file. This is insufficient for safe and correct invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but lacks structure. Given the complexity of the tool (4 parameters, conversion process), it could benefit from brief bullet points or a more detailed breakdown. The length is appropriate but the flat structure limits clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description does not explain the return value or output format, and there is no output schema. The agent does not know what the result of the conversion will be (e.g., a URL or file path). Additionally, siblings like file_converter_render_conversion_report suggest that output handling may be separate, which is not clarified. The description is incomplete for reliable use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter having a clear description in the input schema. The tool description adds no additional meaning beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'convert' and the resource 'file from one format to another', and specifies the scope using CloudConvert with 200+ formats. It distinguishes from siblings like file_converter_encrypt_action, file_converter_merge_action, etc. by focusing solely on format conversion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool should be used when converting file formats, but does not provide explicit guidance on when to use this tool versus alternatives among the many file_converter siblings (e.g., merge, split, encrypt). No exclusions or when-not-to-use conditions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavioral traits. It states the action (password-protect) but does not explain side effects (e.g., whether the original file is modified or a new copy created), auth requirements, or how the result is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences, front-loaded with the action verb, and contains no redundant or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the basic purpose but lacks details about the output format, constraints (e.g., file size limits), and how the result is stored (only implied by output_variable_name). For a simple mutation tool, more behavioral context would be helpful.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds no additional meaning beyond what the schema already provides for each parameter. It does not compensate with extra context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'password-protect' and identifies the resource as a PDF file, clearly distinguishing it from sibling file_converter_ actions like convert, watermark, or merge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives or when not to use it. Usage is implied by the tool's name and simple purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the processing chain and outputs but omits limitations, error handling, supported formats explicitly, or response characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences efficiently convey purpose, process, and outputs. No extraneous text; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description explains return values (searchable PDF and .txt). However, it could mention how to retrieve results via output_variable_name, supported image formats, or file size constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% (input_file_url and output_variable_name have descriptions; language has enum but no description). The tool description adds no extra parameter meaning beyond the schema, so baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Extract text from an image using OCR' and details the chain of operations (image → PDF → OCR → plain text) and outputs (searchable PDF and .txt), distinguishing it from sibling file_converter tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like file_converter_ocr_action. The description implies usage for OCR on images but does not specify exclusions or provide when-not criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It discloses automatic conversion to PDF but lacks details on file size limits, supported formats, or output storage behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no extraneous words. Every part contributes to understanding the tool's function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core function and auto-conversion. Given no output schema and 2 simple parameters, it is mostly complete, though it could mention output variable behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. The description adds no additional meaning beyond the schema; it does not elaborate on URL format or output variable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool combines multiple files into a single PDF and automatically converts non-PDF files. This distinguishes it from sibling tools like split or convert.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for merging files into a PDF but does not explicitly state when to use or avoid this tool, nor does it compare to alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Discloses no credit consumption but omits details like read-only nature, supported file types beyond examples, and error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences with front-loaded purpose and a critical behavioral note. No superfluous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Adequate for a simple 2-param tool with no output schema. Could mention output format (e.g., JSON object) but current description is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with both parameters described. Description adds no extra meaning beyond schema; baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Extract metadata from any file' with specific examples (EXIF, PDF properties, video resolution/duration). Distinct from sibling file converter tools like file_converter_convert_action by explicitly noting no conversion credits consumed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implicit guidance via 'Does not consume conversion credits' suggests using when only metadata needed, saving credits. However, lacks explicit when-not-to-use or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the tool 'Adds a searchable text layer' which implies transformation but not destruction. However, it does not disclose whether the original file is modified, output format, file size limits, or required accessibility of the URL.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action. No unnecessary words. Efficient and clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and multiple sibling file converter tools, the description could be more complete. It does not explain the output (likely a PDF with text layer), file size limits, or how it differs from image_to_text. It covers the core but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67% (2 of 3 parameters have descriptions). The description does not add any parameter information beyond what the schema provides. Since the schema already explains the parameters adequately, the description adds no extra value for parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Add a searchable text layer to scanned PDF files using OCR.' It uses a specific verb ('Add') and resource ('searchable text layer to scanned PDF files'). This distinguishes it from sibling tools like file_converter_image_to_text_action, which likely handle non-PDF images.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use or not use this tool versus alternatives. It implies usage for scanned PDFs, but does not mention alternatives like file_converter_image_to_text_action for non-PDF images or other conversion tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description bears full burden. It states the tool reduces file size while maintaining quality, but does not specify whether compression is lossy or lossless, nor disclose any limitations or side effects. The core behavior is clear, but additional detail could improve transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with action, no redundant information. Every word serves a purpose. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains what the tool does but does not address output format, error scenarios, or return value semantics. Given the absence of an output schema and annotations, more detail would be helpful for an agent to fully utilize the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 75% (3 of 4 parameters documented). The missing 'profile' parameter has enum but no description. The tool description adds no additional meaning to parameters beyond the schema. Baseline 3 is appropriate given coverage level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (compress/optimize), the resource (PDF, PNG, JPG files), and the scope (without changing format). It effectively distinguishes the tool from siblings like file_converter_convert_action (which changes format) and file_converter_encrypt_action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for compression needs where format must be preserved, but it does not explicitly state when to use this versus alternatives like convert or merge. No exclusions or prerequisites are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description bears full burden. It mentions rendering HTML but does not disclose read/write nature, side effects, or dependencies (e.g., requires prior conversion data). Minimal behavioral insight.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, efficient sentence with no redundant information. Brief but front-loaded with key purpose. Slightly room for improvement by adding parameter context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 0% schema coverage, the description is incomplete. It doesn't explain how parameters work or the tool's role in a conversion workflow, leaving gaps for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% with no parameter descriptions. The description adds no meaning to report_data or output_variable_name, failing to compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Renders' and the resource 'file conversion results' with specific output 'HTML report with download links and preview'. This distinguishes it from sibling tools like file_converter_convert_action and other render report tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. No explicit context about prerequisites (e.g., needing a prior conversion step) or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must bear this burden. It discloses the output format (array of URLs) but does not mention behaviors such as whether the original PDF is modified, storage duration of URLs, file size limits, or required access permissions. This leaves some uncertainty about the tool's side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at two sentences, with no redundant or filler content. Each sentence serves a purpose: stating the action and specifying the return value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two required parameters and no output schema, the description is mostly complete. It covers the core operation and output. Minor gaps remain: the nature of the returned URLs (temporary? accessible?) and any prerequisites are not mentioned, but the overall context is sufficient for an agent to understand the tool's role.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds no additional meaning beyond the schema; it does not explain the parameters further or provide usage context for input_file_url or output_variable_name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the action (Split a PDF into one file per page) and the output (array of individual page PDF URLs), distinguishing this tool from other file_converter actions like merge, convert, or optimize.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for splitting PDFs into separate pages but provides no explicit guidance on when to use this tool over alternatives like file_converter_merge_action or file_converter_ocr_action. No when-not-to-use or precondition details are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description burdens full behavioral disclosure. It only states the core function without revealing side effects, such as file overwriting, permission needs, or result storage. This minimal disclosure is insufficient for safe autonomous use.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is direct and free of redundancy. Every word contributes to conveying the tool's purpose, making it highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple utility tool with full schema coverage and no output schema, the description adequately covers the core action. However, it lacks details on limitations (e.g., text size, font, positioning) and result handling, which would improve completeness given the complex sibling context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3 applies. The description adds no extra parameter context beyond the schema's already clear descriptions. It neither enhances nor detracts from the schema's clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Add a text watermark' to 'a PDF or image file', specifying the resource and examples like CONFIDENTIAL, DRAFT. This distinguishes it from sibling tools such as file_converter_convert_action or file_converter_encrypt_action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. Among many sibling tools (e.g., file_converter_convert_action, file_converter_merge_action), there is no mention of conditions or exclusions, leaving the agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It does not disclose behavior like authentication needs, rate limits, or what exactly is returned (e.g., profile slug, URL, or full profile data). The schema mentions returning a 'profile slug,' but the tool description omits this, leaving the agent uncertain about the output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 13 words, instantly conveying purpose. It is front-loaded with the action verb 'Find' and the resource, with no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool, the description is minimally complete. However, it lacks details about the output format or error handling. Without an output schema, the agent cannot fully anticipate the tool's response, making the description somewhat incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter 'query' has a description in the schema that explains it finds the LinkedIn profile slug. The tool description adds no additional meaning beyond what the schema provides. With 100% schema coverage, a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: 'Find someone's LinkedIn profile from a query of their name or other details.' It specifies the verb 'find' and the resource 'LinkedIn profile,' and differentiates from sibling tools like 'get_linkedin_profile' (which likely works with an existing identifier) and 'search_linkedin_people' (which searches with specific criteria).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention when not to use it, prerequisites, or mention sibling tools. An agent would need to infer usage based on the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. It lists operations but fails to disclose side effects, security implications, or behavior beyond the obvious. For example, it does not mention that the tool is non-destructive or that it stores output to a variable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that uses concise language to list core operations. Every word serves a purpose, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (4 parameters, no output schema), the description adequately covers the high-level purpose but omits details like the output storage mechanism and delimiter usage. It is minimally complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description does not need to add parameter details. The description adds no additional meaning beyond the schema, providing a baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Change casing, remove characters, split text, remove HTML, or truncate text' clearly lists several text transformation operations, making it clear this is a general text formatting tool. However, it does not mention all format types in the enum (e.g., join_text, convert_to_json), and it lacks specificity that would distinguish it from unrelated siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor any conditions or prerequisites. It simply lists capabilities without contextual cues for agent selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It only states 'create images' without explaining output format, error handling, rate limits, or any side effects. This is insufficient for a tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 12 words, front-loaded with the action, and contains no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 required parameters with enums and no output schema, the description is too brief. It lacks information about the return value (e.g., image URL) and any prerequisites or post-conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds minimal value, only echoing that options exist for style and aspect ratio. It does not correct the misleading schema description for 'model' (which says 'text generation').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'create' and the resource 'images using AI models', with specific options for style and aspect ratio. It effectively differentiates from sibling tools focused on research or text generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'social_post_creator_generate_social_image_action' or 'youtube_thumbnail_generate_packaging_action'. There is no mention of when-not-to-use or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided; description only states 'Fetch recent posts' without disclosing behavior for invalid handles, rate limits, pagination, or response format. Agent lacks critical context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loads key information. No extraneous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple, but missing output schema and usage guidance relative to siblings reduces completeness. Agent doesn't know return structure or when to prefer this over search_bluesky_posts.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and already describes both parameters. Description adds no additional meaning beyond schema, meeting baseline expectation for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states verb 'Fetch', resource 'recent posts', and source 'specified Bluesky user handle'. Differentiates from siblings like post_to_bluesky (posting) and search_bluesky_posts (keyword search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as search_bluesky_posts. Agent must infer, increasing risk of incorrect tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states the action without disclosing read-only nature, performance implications, rate limits, auth requirements, or side effects. For a tool with no annotations, this is insufficient transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that is front-loaded with the action. Every word adds value, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters and no output schema, the description is too brief. It does not mention return format, ordering, pagination, error handling, or how the multiple filters interact. A more comprehensive description is needed for this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds minimal value beyond what the schema already provides for each parameter. It does not explain parameter interactions or provide additional context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (Build) and resource (list of calendar events), and specifies the supported providers (Google Calendar, Outlook, or all). This distinguishes it from sibling tools like enrich_calendar_event or meeting_prep tools that focus on single events or meeting preparation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. There is no mention of prerequisites, context, or when not to use it. Among siblings, many meeting-related tools exist, but no direct comparison or exclusion criteria are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, and the description does not disclose behavioral traits such as whether the operation is read-only, required permissions, rate limits, or what 'enriched' means in terms of data quality. The description is insufficient for an agent to understand side effects or constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no unnecessary words. It is concise but lacks structural elements like sections or bullet points.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (1 param, no output schema), the description provides minimal context. It omits expected return value details, pagination behavior, or any error conditions. An agent would need additional inferences to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with the parameter 'domain' already described. The description adds 'enriched company data' but does not enhance understanding of the domain parameter's format or constraints beyond the schema. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'gather' and the resource 'enriched company data' with source 'Breeze Intelligence'. However, it does not differentiate from many sibling tools focused on company research (e.g., company_research_v2_get_report, get_hubspot_company_object), so it lacks distinctiveness.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or exclusions. The description is purely functional without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It only states 'fetch', implying read-only, but does not confirm no side effects, auth requirements, or rate limits. Minimal behavioral insight beyond basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. Front-loaded with the core action and benefit. Efficient and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description does not explain return values, result format, pagination, or error handling. Parameters like max_documents_count hint at limits but are not elaborated. The description leaves an agent uncertain about what to expect from the results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with parameter descriptions explaining each field. The description adds little extra meaning beyond 'filtering criteria'. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it fetches semantic search results from a builder's knowledge base. The verb 'fetch' and resource 'builder's knowledge base' are specific. However, it does not distinguish from sibling tools like 'query_agent_kb' or 'get_data_from_user_uploaded_files', leaving ambiguity about what 'builder' refers to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions 'for data analysis', giving a hint about when to use, but no explicit guidance on when not to use or alternative tools. The context is implied, not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It states 'retrieve semantic search results' but does not specify that the operation is read-only, how results are scored or chunked, or any authentication/rate limit requirements. The description adds minimal behavioral context beyond the generic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of 10 words, which is concise but lacks necessary detail for a tool with 5 required parameters. While front-loaded, it is underspecified and could benefit from additional sentences to cover key aspects like return value or filtering behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 required parameters, no output schema, no annotations, and operates on user-uploaded files, the description is incomplete. It does not explain the format of results, how files are accessed, or any constraints. The description fails to provide sufficient context for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all 5 parameters adequately. The tool description adds no additional meaning or context beyond what is in the schema, meeting the baseline for parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves semantic search results from user-uploaded files, using a specific verb and resource. However, it does not differentiate from the sibling tool 'get_data_from_builder_knowledge_base', which likely performs similar retrieval from a different source.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as other search or retrieval tools in the sibling list. There are no explicit exclusions, prerequisites, or usage examples beyond what is implied by the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must fully disclose behavior. It only states basic functionality without revealing important traits like output format, pagination, rate limits, or authentication needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words, efficiently conveying the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description lacks details about return values, source (Google News), language, or limitations, making it incomplete for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has full description coverage (100%), so baseline is 3. The description adds no extra meaning beyond what the schema provides, merely mentioning queries and date ranges.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Fetch news articles' and identifies resources (queries, date ranges) and purpose (monitoring topics/trends), clearly distinguishing it from general search tools like get_search_results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for news monitoring but does not provide explicit guidance on when to use this tool versus alternatives such as get_search_results or search, nor does it mention when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully convey behavioral traits. It does not mention any side effects, authorization needs, rate limits, or return format beyond the basic functionality. The default behavior is partially explained via the schema but not in the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that efficiently conveys the core purpose without unnecessary words. It is well front-loaded and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple retrieval tool with one parameter and no output schema, the description provides adequate context: it retrieves company data and outlines the two usage modes. However, it could be slightly improved by noting the typical return fields or expected behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for the single 'query' parameter, describing its default and search purpose. The description adds no further parameter semantics beyond what the schema already gives, meeting the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves company data from HubSpot, specifying two modes: by query or most recent company. This distinguishes it from other HubSpot tools like get_hubspot_contact_object or get_hubspot_object.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as get_hubspot_object or other company-related tools. The description does not mention when-not-to-use or contrast with siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry full behavioral disclosure. It fails to mention that the query parameter defaults to '_most_recent_contact' for missing or short queries (though present in schema). It also omits details on return format, error handling, or read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, using one sentence that is front-loaded. However, it could benefit from slightly more structure to separate the two retrieval modes clearly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should clarify what 'contact data' entails. It does not specify return fields, pagination, or error behavior, leaving the agent underinformed for a tool with a required parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description covers the parameter fully at 100% coverage. The tool description adds little beyond restating the purpose, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves contact data from HubSpot and distinguishes between query-based retrieval and fetching the most recent contact. This makes the purpose specific and distinct from sibling tools like get_hubspot_company_object.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage contexts (query or most recent contact) but provides no explicit guidance on when to use this tool versus alternatives like get_person_object or contact_research. No when-not details are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. Description implies read-only retrieval but does not explicitly state side effects, authentication requirements, or rate limits. The default query behavior is partially hidden in the schema parameter description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with key information. No extraneous text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no output schema, no nested objects), the description covers the basic purpose. However, it does not address error handling, pagination, or response format, which could be relevant.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and each parameter has a description. The tool description adds some context about defaults for query, but this is already present in the schema. So it meets the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves data for any supported HubSpot object type or the most recent object. It differentiates from siblings like get_hubspot_company_object by being generic, but does not explicitly call out the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus the more specific sibling tools (e.g., get_hubspot_company_object, get_hubspot_contact_object). No alternative mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description indicates a read operation ('retrieve') but does not disclose behavioral traits like authentication requirements, rate limits, or pagination. For a simple retrieval tool, this is minimally adequate but leaves gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.