Box

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

Annotations already indicate read-only, idempotent, non-destructive behavior. Description adds that it probes LLMs and returns scores, and that using an API key sends data to Anthropic. No contradictions, and extra context about the free default model is helpful.

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 main purpose, no waste. Each sentence adds essential information efficiently.

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 strong annotations, the description covers the tool's purpose, parameters, use cases, and return structure. Could mention rate limits or data privacy for Anthropic, but overall it's 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 covers all parameters with descriptions. The description adds meaning beyond schema by explaining the default model, the role of `_apiKey` (BYO key for Anthropic), and how `context` disambiguates names. This adds 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 verb ('Probe', 'score'), the resource ('LLMs', 'visibility'), and distinguishes from siblings like 'scan_competitor_ai_presence' by focusing on probing multiple models and scoring visibility.

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?

Provides context for when to use (AI-marketing audits, pre-launch checks, competitive monitoring) but does not explicitly mention when not to use or compare to siblings. The context is clear enough for an agent to infer appropriate usage.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds valuable context: returns structured answers with stable pipeworx:// citation URIs, which is beyond what annotations provide. No contradictions with 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 detailed but well-structured, starting with a clear directive ('PREFER OVER WEB SEARCH'). Every sentence adds value, listing examples and sources. It could be slightly more concise, but the front-loading and organization make it 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 the tool's complexity (routes to 3,336 tools), the description covers purpose, usage, and return format. It does not mention limitations like rate limits or handling of ambiguous queries. With annotations providing safety and idempotency, it is fairly complete but could include such caveats.

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 all parameter aliases described. The description adds the context of accepting natural language queries but does not provide additional semantics beyond the schema. The schema fully documents the parameter, 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 answers factual questions about current/historical data from many sources (SEC filings, FDA data, etc.), explicitly preferring over web search. It lists specific domains and example queries, making the purpose unmistakable and differentiating from 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 explicitly says 'PREFER OVER WEB SEARCH' and gives extensive examples of when to use, such as for 'what is', 'look up', etc. It does not explicitly mention when not to use, but the strong preference indication and coverage of factual queries effectively guide usage. Sibling tools like entity_profile are not mentioned as alternatives, which would be a minor improvement.

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?

Description provides deep behavioral coverage beyond annotations: resolver contract, match confidence levels, parent event extraction, news fallback, closed market handling, wide spread warnings. All annotations (readOnly, idempotent, openWorld, non-destructive) are consistent with described 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?

Well-organized with section headers (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, etc.), though lengthy. Each section serves a clear purpose; sentences are informative but several could be condensed. Still, for the complexity, structure is good.

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, so description fully covers return fields: market, analysis, evidence, resolver contract (match confidence, alternatives, suggestions), parent event, news metadata. Also covers edge cases (low confidence, closed markets, wide spreads) and blocking mechanisms. Very comprehensive.

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 has 100% coverage with descriptions; description adds examples for market_input, explains depth default with effect on sources, and details include_raw impact on response size. Adds meaningful context beyond structured 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?

Clearly states the tool researches a single Polymarket bet by pulling Pipeworx data, resolving market, classifying, and returning evidence. Distinct from sibling tools (e.g., polymarket_edges) which focus on edge across markets.

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?

Explicitly tells agent to use for 'should I bet on X', 'what does the data say', or 'is there edge in Z'. Also explains conditions of non-use (low confidence, closed markets, illiquid spreads) through safety notes, guiding correct invocation.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds specific return fields and clarifies the tool's purpose, providing useful behavioral context without contradiction.

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 action and key detail (file ID), second lists return fields and usage guidance. No wasted words, front-loaded with essential info.

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 simple tool (single parameter, safe read), annotations provide safety profile, and description covers purpose, output, and usage timing. No gaps for an agent to select and invoke 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 coverage is 100% and the parameter description in the schema is clear. The tool description does not add extra meaning beyond what the schema provides, so baseline score of 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 it returns full metadata for a single file, lists specific fields, and distinguishes from siblings like box_get_file_text by focusing on metadata. It also provides usage context.

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?

Explicitly says 'Use after listing or searching to inspect one document,' giving clear context for when to invoke this tool. It does not explicitly exclude alternatives but implies it's for detailed inspection after broader queries.

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?

Annotations already declare readOnlyHint and destructiveHint, but the description adds important behavioral details: content is capped at ~100,000 characters with truncation flagging, and binary formats produce unreadable output, providing complete 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 extremely concise at two sentences, front-loads the core action, and efficiently conveys all key information without 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 the tool's simplicity (one parameter, no output schema), the description covers purpose, appropriate file types, and limitations well. The 'flagged when truncated' detail could be expanded, but overall it's complete enough.

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?

With 100% schema coverage, the single parameter file_id is adequately described in the schema. The description reinforces its role but adds no new semantic detail, warranting the 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 downloads and returns text content of a Box file by file ID, specifies it's best for plain-text formats like Markdown and CSV, and distinguishes from binary formats, making the purpose unambiguous.

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 gives explicit guidance on when to use (text documents) and when not (binary formats, which yield unreadable bytes), and mentions the truncation limit. However, it doesn't explicitly contrast with sibling tool box_get_file.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds that it returns specific profile fields and requires authentication ('signed-in'), providing useful behavioral context beyond the 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?

Two sentences, no wasted words. Front-loaded with the action and resource. Ideal for quick understanding.

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 no parameters and no output schema, the description fully explains what it does, what it returns, and common use cases. No 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?

No parameters exist, so schema coverage is trivially 100%. Description adds no parameter info, but baseline for zero parameters is 4.

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 the signed-in Box user's profile and lists specific fields (id, name, email, storage). It distinguishes from sibling Box tools that deal with files or folders.

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?

Explicitly recommends use for identifying the connected account or reporting storage usage. No explicit exclusions, but context is clear given simplicity of the tool.

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?

Annotations already indicate safe, non-destructive, idempotent behavior. The description adds value by listing the specific return fields (id, type, name, size, last-modified), which is useful beyond what annotations convey.

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, no wasted words. Front-loaded with purpose and default behavior, then return format. 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?

Given the tool's simplicity, strong annotations, and clear parameter schema, the description fully covers what an agent needs: purpose, invocation guidelines, and output format. No 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 coverage is 100% with good descriptions. The description adds a useful default for folder_id (root folder if omitted) but does not clarify limit beyond what schema says. 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?

Clearly states it lists files/subfolders in a Box folder, with specific resource and action. However, it does not explicitly distinguish this tool from siblings like box_search or box_get_file, leaving some ambiguity about when to use this one.

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?

Provides guidance on passing a folder id or omitting for root folder, but no when-to-use vs alternatives, nor when not to use. Usage context is implied but 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?

Annotations already indicate read-only, idempotent, safe behavior. Description adds that it returns specific fields (id, type, name, size, last-modified) and searches across names and content, providing useful behavioral context beyond 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?

Two sentences, each conveying essential information. No fluff, front-loaded with core functionality.

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, but description explains return fields well. Mentions optional filters and limit. Could note pagination or scope (user's account), but overall complete for typical search 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 coverage is 100% with descriptions. Description adds context: query matches across names and content, limit defaults to 30 max 200, type filter optional. Adds 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 clearly states the tool searches a user's Box account for files and folders by query string across names and content. It specifies optional filters and return fields, distinguishing it from siblings like box_get_file.

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?

Explicitly says 'Use to find documents by keyword,' providing clear context for when to use. Does not explicitly exclude alternatives, but context is sufficient.

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?

Beyond annotations (readOnlyHint, idempotentHint), the description adds critical behavioral details: the data sources (SEC EDGAR/XBRL, FAERS), the fix for off-calendar fiscal years, sorting by primary metric, and citation URIs. No contradictions with 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 paragraph that efficiently conveys all necessary information without waste. It front-loads the core purpose and usage, then provides technical details. Slightly more structured bullet points could help, but it's concise overall.

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 (two entity types, multiple data sources, no output schema), the description is remarkably complete. It explains the data returned, sorting, accuracy fixes, and citation URIs, leaving minimal ambiguity for an AI 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 100%, so baseline is 3. The description enhances this by specifying the format for values (tickers/CIKs for company, drug names) and clarifying the enum for type. It also explains the data context for each type.

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 compares 2-5 companies or drugs side by side, with specific verbs like 'compare' and 'rank-by-metric'. It distinguishes from siblings by noting it replaces multiple sequential lookups, setting it apart from other analysis 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?

The description explicitly lists query patterns like 'compare X and Y' and 'which is bigger', and explains when to use each entity type. While it doesn't specify when not to use it, the examples provide clear contextual guidance.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds context that results are ready to call directly and no second schema lookup is needed. This provides additional behavioral insight beyond 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 focused paragraph, front-loading the core purpose and usage. Every sentence adds value, and it is efficiently structured without 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?

For a discovery tool with 6 parameters and no output schema, the description explains the return value (tool names, descriptions, schemas) and gives context on the query parameter. It is complete enough 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% with descriptions for all parameters. The description adds extra context by listing aliases and providing examples, enhancing understanding of the 'query' parameter beyond the 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 tool's purpose: 'Find tools by describing the data or task.' It lists specific data domains and explains the output (top-N tools with names, descriptions, full schemas). It distinguishes itself from siblings as a discovery tool.

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?

Explicit guidance provided: 'Use when you need to browse, search, look up, or discover what tools exist for...' and 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This clearly indicates when to use and implies it is not for direct data retrieval.

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?

Description adds significant behavioral context beyond annotations: explains return fields, patent limitations, and fundamentals fix. No contradiction with annotations (readOnlyHint, idempotentHint, etc.).

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?

While every sentence adds value, the description is lengthy. It is front-loaded with purpose but could be slightly more concise without losing critical details.

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 (multiple data sources) and no output schema, the description fully explains return components, limitations, and fallbacks, making it complete 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 100% but description adds meaning: explains 'type' is only company, 'value' can be ticker or CIK with zero-padding requirement, and names unsupported.

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 'everything about a US public company in one call.' It distinguishes itself from siblings like 'resolve_entity' for name resolution.

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?

Explicitly states when to use (user asking about a company) and when not to (names not supported, use resolve_entity first). Provides clear context and alternative.

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?

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description's 'delete' aligns with them. However, the description adds no behavioral traits beyond usage context (e.g., no mention of side effects or reversibility). With strong annotations, this is adequate but not enhanced.

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 clear sentences: the first defines the action, the second provides usage guidance and pairing. No extraneous words; every sentence 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 tool with one parameter, no output schema, and clear annotations, the description fully covers purpose, when to use, and complementary tools. An agent can correctly select and invoke this tool without ambiguity.

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 one parameter 'key' described as 'Memory key to delete.' The tool description does not add further meaning beyond the schema, 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 states 'Delete a previously stored memory by key,' providing a specific verb (delete) and resource (memory by key). It distinguishes from sibling tools 'remember' (store) and 'recall' (retrieve), making the purpose unambiguous.

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 gives explicit scenarios for use: 'when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' It also suggests pairing with 'remember' and 'recall,' but lacks explicit when-not-to-use guidance 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. The description adds value by detailing the fetch-extract-emit process and output format, which is consistent with 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 concise: three sentences with clear front-loading of purpose, process, and use cases. 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?

Given no output schema, the description explains the return format ('a single text blob'). It covers the process and output sufficiently for a simple tool with two parameters.

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 description adds little beyond the schema. It repeats the url purpose but omits the default and max for max_links. 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 specifies the verb 'generate', the resource 'llms.txt for any URL', and the purpose 'so AI crawlers can index the site cleanly'. It distinguishes itself from siblings like 'scan_competitor_ai_presence' by focusing on file 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?

Explicit use cases are given: getting a client's site indexed, drafting for own project, or auditing. It provides clear context but does not explicitly state when not to use or list 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?

Discloses rate limiting (5 per identifier per day), free usage, no tool-call quota impact, and that team reads digests daily. Annotations provide no contradictory info; this adds value beyond them.

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 covering purpose, usage, and constraints. Front-loaded with purpose, efficient and 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?

For a simple feedback submission tool, the description covers what to send, how to format, and constraints. No output schema needed; this 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 covers all parameters with descriptions (100% coverage). Description adds guidance on message length (2000 chars max, 1-2 sentences), specificity, and format. Baseline 3, plus extra 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 is for giving feedback to the Pipeworx team about bugs, missing features, data gaps, or praise. It distinguishes from sibling tools by being a feedback channel rather than a data retrieval or analysis tool.

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?

Explicitly lists use cases: bug, feature, data_gap, praise. Advises against pasting end-user prompts and mentions rate limits. Could contrast more with sibling tools, but the context makes it 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?

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds beyond annotations by noting the data source (CF analytics-engine), lack of PII, and caching behavior (5min-1h). No contradictions.

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 front-loaded with key information and uses a structured list for use cases. It is informative but slightly verbose; still efficient overall.

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 that there is only one parameter and no output schema, the description is quite complete. It specifies return types (top tools, top packs, total call volume) and caching details.

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 one parameter having an enum and description. The description adds further context about the window parameter, explaining that shorter windows surface what's hot right now and longer windows show steady-state demand.

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 that the tool returns top tools, top packs, and total call volume over recent windows (24h, 7d, 30d). It distinguishes itself from sibling tools by focusing on aggregated trends rather than specific entity queries or file 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?

Three explicit use cases are provided (discovering hot data sources, confirming canonical choice, seeing use case alignment), giving clear context. However, it does not explicitly state when not to use it or what alternatives exist.

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?

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds substantial behavioral context: modes, partition checks, similarity thresholds, filter logic, and response structure. No contradictions with 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 detailed but well-structured, with clear sections for modes and filters. It front-loads the core purpose. While somewhat lengthy, each sentence contributes necessary information for a tool with two modes and complex logic.

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 (two modes, multiple checks, filters, response format) and no output schema, the description is remarkably complete. It covers all key aspects: input parameters, mode behavior, filters, and output structure.

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?

Both parameters (event and topic) have descriptions in the schema, achieving 100% coverage. The description adds semantic value by explaining how each parameter is used (event mode vs. topic mode, slug vs. seed question), which goes beyond the schema's brief descriptions.

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 finds arbitrage opportunities on Polymarket using monotonicity violations and partition-sum checks. It explicitly describes two distinct modes (event and topic), distinguishing it from sibling tools like polymarket_edges.

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 explicit guidance on when to use each mode (event for a single event slug, topic for cross-event search). It explains scenarios where cross-event mode catches patterns missed by single-event mode and outlines filters (e.g., placeholders, similarity threshold). However, it does not directly contrast with alternatives like polymarket_edges or polymarket_kalshi_spread.

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?

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as true/false appropriately. The description adds extensive behavioral details: model families, edge calculation with slippage, per-segment filters, caching at 1h, and diagnostic output, going well beyond what annotations alone provide.

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 detailed and well-structured with clear segmentation (by_segment, knobs, diagnostics). It is slightly verbose but every sentence adds value, no redundancy. Could be trimmed slightly for efficiency, but overall effective.

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 of 9 parameters and no output schema, the description is remarkably complete, covering input knobs, output structure, segments, diagnostics, and caching. It compensates for the lack of an output schema by explaining return fields and behavior in detail.

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%, baseline 3. The description adds substantial semantic value by explaining the purpose and effect of each parameter, such as min_liquidity recommending $5000 to avoid thin-book opportunities and min_partition_leg_kelly clarifying its interaction with min_kelly.

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 scans Polymarket markets to find opportunities where Pipeworx data disagrees with market price, specifically for betting decisions. It distinguishes from sibling tools by its unique data source and focus on actionable edges.

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 tool is built for 'what should I bet on today' and helps agents avoid paging hundreds of markets, providing clear context. However, it does not explicitly exclude alternatives or provide when-not-to-use guidance, though siblings like polymarket_arbitrage exist.

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?

Beyond annotations (readOnlyHint, etc.), description details safety fields (compatibility_warning, temporal_alignment, skipped counters) and explains conditions that make spreads meaningful or meaningless, offering deep 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?

Well-structured with sections (TWO MODES, RESPONSE, SAFETY FIELDS) but verbose and contains explanations that could be streamlined for 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?

Despite no output schema, description comprehensively explains return structure, all safety fields with conditions, and temporal considerations, fully covering 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 has 100% coverage with clear descriptions; description adds context on overriding behavior and shortcut values, slightly enhancing understanding 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 clearly defines the tool as a cross-venue spread analyzer between Kalshi and Polymarket, distinguishing it from siblings like polymarket_arbitrage by focusing on same resolving question across venues.

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?

Provides explicit context for two modes (topic shortcuts vs explicit tickers), explains when compatibility warnings trigger, and cautions that pre-mapped topics may not be tradeable, guiding appropriate usage.

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 adds context beyond annotations: scoping to identifier and pairing with remember/forget. Annotations already indicate readOnly and idempotent, so the description complements them.

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 multiple sentences, front-loaded with the main purpose, and each sentence provides necessary information without waste.

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 is complete for a simple read-only tool with one optional parameter, covering behavior, scoping, and related tools. No output schema, but return format is implied.

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 has 100% coverage and the description explains the key parameter's behavior (omit to list all keys), adding value beyond the schema's 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 states a specific verb ('Retrieve') and resource ('a value previously saved via remember'), and distinguishes from sibling tools like 'remember' and 'forget'.

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 explains when to use the tool ('to look up context the agent stored earlier') and mentions scoping, but does not explicitly state 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?

Describes parallel fan-out to SEC EDGAR, GDELT/GNews fallback, and USPTO with soft-fail note. Explains return structure (changes[], total_changes, citation URIs). Annotations already indicate read-only, but description adds rich behavioral details beyond that.

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?

Description is thorough and front-loaded, but somewhat long. Each sentence adds value, but it could be slightly more concise without losing 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 no output schema, the description explains return format. Covers source behavior, parameter details, and limitations (USPTO soft-fail). Provides complete guidance for an agent to use the tool 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 has 100% coverage, but description adds context: explains 'since' accepts ISO date or relative shorthand, gives examples, and notes that the tool fans out to multiple sources. This goes well beyond the schema descriptions.

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 retrieves recent changes for a company in a time window, with examples like 'what's happening with X'. It distinguishes from sibling tool entity_profile, which is for static 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?

Explicit use cases are provided ('Use for 'what's happening with X', 'updates on Y'...'). Also explicitly tells when not to use it and suggests alternative: 'Use entity_profile instead when you want the static profile regardless of window.'

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?

Annotations provide idempotentHint, description adds context about persistence (authenticated users vs anonymous 24-hour retention) without contradiction.

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?

Four front-loaded sentences with no wasted words; every sentence serves a 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 key-value store with complete schema and annotations, the description fully covers purpose, usage, and behavioral expectations.

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% with clear descriptions. Description adds context about scoping by identifier, slightly enhancing 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?

Clearly states it saves data for reuse across conversations/sessions using specific verbs and resources. Distinguishes from sibling tools recall and forget.

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?

Explicitly says when to use (when discovering something worth carrying forward) and mentions alternatives (recall to retrieve, forget to delete).

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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds value by noting internal cascading through multiple lookup endpoints, which is useful behavioral context beyond the 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?

Concise and well-structured. Purpose is front-loaded, followed by type-specific details. Every sentence adds value; no redundancy or waste.

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 lacking an output schema, the description fully explains the return values for both types (ticker+CIK for companies, RxCUI for drugs) and mentions citation URIs. This provides complete context for an agent to understand what the tool returns.

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. The description adds significant meaning: explains accepted input formats (ticker, CIK, or name for companies; brand/generic for drugs) and mentions auto-disambiguation, which goes beyond the schema's enum and 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 resolves user-spoken names to canonical IDs. It specifies supported types (company, drug) and their return values, distinguishing it from siblings like compare_entities or entity_profile.

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?

Explicitly tells when to use ('Use FIRST when you have a name but need an ID') and explains it replaces multiple manual lookups. Provides usage context without explicitly stating when not to use, which is acceptable given the clear 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?

Beyond annotations (readOnly, idempotent, non-destructive), the description reveals that it internally calls ai_visibility_check for each entity, ranks them, and returns a ranked list with score, confidence, signal density. Since there is no output schema, this behavioral detail is crucial and adds significant value.

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 plus a parenthetical example, all front-loaded with the core action. Every sentence adds value: purpose, method, use case, and output. No waste.

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 of a multi-entity comparison tool with no output schema, the description covers return structure, internal mechanism, purpose, and parameter nuances. It is complete for an agent to select and invoke correctly, especially with rich annotations and 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% with detailed descriptions for all 4 parameters. The description adds minor extra semantics: clarifies that the first entity is the 'subject' and that context disambiguates common names. This goes slightly beyond the schema, but the schema already does most of the work.

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 compares AI visibility across multiple entities side-by-side, with a specific verb 'compare' and resource 'AI visibility'. It distinguishes from sibling tools like ai_visibility_check (single entity) and compare_entities (generic comparison) by emphasizing the AI visibility domain and ranking. The example 'does Claude know about us as well as our competitors?' grounds the 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?

The description specifies use for competitive AI-marketing audits and mentions the first entity as the 'subject'. It implies when to use (multi-entity comparison) but does not explicitly state when not to use or mention alternatives like using ai_visibility_check multiple times. However, the context is clear and sufficient for most agents.

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?

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description adds important context: composite external calls, partial failure (bundlephobia timeout), and first-measurement delay. No contradictions.

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?

Description is dense but well-structured, front-loading the key composite nature and listing return fields. Could be slightly more concise, but minimal waste for the amount of info.

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 no output schema, the description fully explains return structure (summary block, advisories, links, alternatives), constraints (NPM only), and failure modes (partial degradation). No 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?

Parameters are fully documented in schema (100% coverage). Description adds that scoped packages are accepted and version defaults to latest, but does not introduce new constraints 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 precisely states the tool's purpose: a composite check for npm packages across deps.dev and bundlephobia, returning license, security, size, and ESM support. It clearly distinguishes from siblings by defining a specific composite use case.

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?

Explicitly states when to use: when agent asks about safety, popularity, size, or cost of adding a package. Also notes NPM-only in v1 and partial failure behavior. Missing explicit when-not-to-use, but ecosystem restriction is 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?

The description adds significant behavioral context beyond annotations: it specifies the output format (verdict types, citation, delta), the data source (SEC EDGAR + XBRL), and that it replaces multiple sequential calls. Annotations already indicate read-only and idempotent, so the description enriches 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 two concise paragraphs with clear structure: purpose and usage in first, capabilities and output in second. No redundant information; 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?

The description covers purpose, usage, domain limitations, output format, and efficiency gains. With only one parameter and no output schema, it provides all necessary context for an agent to decide and invoke 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?

The single parameter 'claim' has schema description coverage at 100% with a detailed description and examples. The description adds value by clarifying that the input is a natural-language statement, not a structured query, which is beyond the basic type 'string'.

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 fact-checks natural-language factual claims against authoritative sources. It specifies the action (validate, confirm/refute) and the resource (authoritative sources). The tool's function is distinctly different from sibling tools like 'entity_profile' or 'compare_entities'.

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 when an agent needs to check whether something a user said is true' and provides example queries. It also defines the supported domain (company-financial claims for US public companies). However, it does not explicitly state when not to use it or list alternative tools.

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