Close Crm

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

Adds significant behavioral context beyond annotations: default model, free vs paid (BYO key for Anthropic), and describes return structure (score, confidence, signals, raw_response).

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 efficiently pack all necessary information: what tool does, default behavior, optional cost info, return structure, and use cases. No wordiness.

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 4 parameters all described and no output schema, the description properly explains return values and behavior. Annotations cover safety. Complete for the tool's 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 coverage is 100%, so description doesn't need to repeat param details, but it adds practical context (e.g., 'free default', 'BYO key') and examples for entity parameter, enhancing 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?

Clearly states the tool probes LLMs for brand/product/topic visibility and returns a score. Distinct from siblings as no other tool offers this AI auditing functionality.

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 mentions use cases (AI-marketing audits, pre-launch checks, competitive monitoring) and explains when to pass an API key. Could mention when not to use but context 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as safe. The description adds value by detailing that the tool routes to 3,300 tools, fills arguments, and returns structured answers with stable citation URIs. No contradiction 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 front-loaded with a bold 'PREFER OVER WEB SEARCH' directive. Each sentence adds critical information: scope, examples, and return format. It is slightly lengthy due to the example list but remains 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 the tool's complexity (routing to many tools), the description adequately covers how it works and what it returns (structured answer with citations). No output schema exists, but the description compensates by stating the return type. Could include more detail on the 'pipeworx://' URIs.

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 clear descriptions for the required 'question' parameter and its aliases. The description reinforces that the parameter accepts natural language questions and provides examples, adding value beyond the schema itself.

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 tool's purpose: to answer factual questions about current or historical data from structured sources, explicitly stating preference over web search. It lists many domains and distinguishes itself from sibling tools by emphasizing its ability to route to 3,300 tools across 737 sources.

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 when to use this tool ('PREFER OVER WEB SEARCH') and provides example queries. It implies use over alternatives but does not give explicit when-not-to-use or mention specific sibling alternatives, though the sibling list includes many relevant 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?

Annotations indicate read-only, idempotent, non-destructive behavior. The description goes far beyond, detailing low-confidence short-circuiting, closed-market handling, wide-spread market warnings, resolver contract, parent event extractor, and news fallback mechanisms.

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 lengthy, the description is well-structured with clear sections (CLASSIFIERS, FAN-OUT EXAMPLES, etc.). Every sentence adds value, and the first sentence immediately 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?

No output schema exists, but the description thoroughly explains return fields: result.market, result.analysis, result.evidence, resolver contract, parent event extractor, news fields, and safety statuses. An agent can fully understand what to expect.

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 three parameters are fully described in the schema (100% coverage). The description adds valuable context: market input can be slug, URL, or question text; depth default is 'thorough'; include_raw default false with explanation of payload size trade-off.

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 a Polymarket bet by pulling Pipeworx data, with examples of input formats (slug, URL, question text). It explicitly lists classifiers and fan-out examples, making the purpose unmistakable and 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 use cases: 'should I bet on X', 'what does the data say about Y', 'is there edge in Z'. It also explains when the tool returns low-confidence or closed-market statuses, guiding appropriate 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=true, destructiveHint=false, so safety profile is clear. The description adds return fields (display name, description, etc.), which is useful but not beyond what annotations imply.

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 fluff, front-loaded with purpose and ID format. 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?

No output schema, but description lists key return fields. Annotations provide safety context. Lacks mention of pagination or error handling, but overall sufficient for a single get 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 both parameters described. The description does not add new meaning beyond the schema's lead_id format and apiKey use.

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 ('get') and resource ('lead') with explicit ID format ('lead_...'), clearly distinguishing from sibling tools like close_search_leads or close_list_activities.

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 have a Close lead ID and need full details, but lacks explicit when-not-to-use or alternatives. Context is clear from the verb and input schema.

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 false. The description adds value by detailing the return structure (data array, has_more, total_results) and pagination behavior, 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?

Highly concise: two sentences covering purpose, output, and usage. No redundant information, each sentence serves a distinct 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 read-only list tool with no output schema, the description adequately covers return format and pagination. Could mention error cases, but overall complete for typical 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 coverage is 100%, but the description adds context beyond the schema: mentions lead_id requirement, pagination parameters, and notes _limit max of 200 (not in 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 'List activities for a lead' and enumerates the activity types (calls, emails, etc.), distinguishing it from sibling tools like close_get_lead and close_list_contacts.

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?

Specifies required parameter (lead_id) and pagination with _limit and _skip. Does not explicitly state when not to use, but context 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?

Annotations already indicate read-only, idempotent, non-destructive. Description adds return format details (data array with fields, has_more, total_results) and pagination behavior, which is consistent and adds 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?

Two concise sentences, front-loaded with the main purpose, no wasted words. Structure is clear and easy to parse.

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 explains the return format and pagination. Given the simple nature of the tool and rich annotations, the description is sufficient 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 covers 100% of parameters with descriptions, so baseline is 3. The description echoes the filtering and pagination parameters but does not add significant new meaning 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 action 'List contacts (people) in Close', specifying the resource and action. It distinguishes from sibling tools like close_list_activities by focusing on contacts.

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 optional lead_id filtering and pagination via _limit/_skip. Does not explicitly mention when to avoid using or alternatives, but sibling tool names imply differentiation.

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. Description adds that the tool returns paginated results and explains the output structure, 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?

The description is two sentences with no wasted words. It front-loads the purpose, then lists return fields and usage notes. 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?

No output schema, but description explains the return format sufficiently (data array with fields, has_more, total_results). Covers pagination and filtering. Minor omission: no error handling or rate limit info, but adequate for typical 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 has 100% coverage for parameter descriptions, but the description adds practical context: explains that lead_id scopes to one lead, and that _limit/_skip are for pagination, enhancing understanding beyond schema alone.

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 lists opportunities (pipeline deals) in Close, specifies the returned fields (data array with id, lead_id, status, etc.), and distinguishes itself from sibling tools like close_get_lead or close_list_activities by explicitly naming the resource.

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 clear guidance on using lead_id to scope to one lead or omitting for organization-wide listing, plus pagination with _limit/_skip. However, does not explicitly state when not to use this tool (e.g., if a single opportunity by ID is needed).

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, destructiveHint false, openWorldHint true, idempotentHint true. Description adds value by specifying return fields and key source, but does not disclose additional behavioral traits beyond what annotations 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?

Two sentences, no wasted words, action first. Front-loaded with main purpose and ends with specific use case.

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 adequately lists return fields and purpose. Tool is simple (1 required param) and description covers verification and discovery fully.

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% for the single parameter, so baseline is 3. Description adds minimal extra context ('Settings → API Keys') but does not significantly improve semantics 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?

Description clearly states the verb 'Get' and the resource 'current Close user and organization', listing specific return fields (user ID, name, email, organizations). It distinguishes from sibling tools like close_get_lead by focusing on the authenticated user and key verification.

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?

Description gives explicit use case: 'verify the key works and discover your organization context.' While it doesn't state when not to use it, the context and sibling tools make it clear this is the appropriate tool for user/auth info.

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, and non-destructive behavior. The description adds valuable context beyond annotations: it explains the response structure (data array, has_more, total_results) and the query language, enhancing 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: two sentences that pack in purpose, response format, query syntax, and pagination. Every sentence adds value with no fluff.

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 and the rich schema coverage, the description is complete. It explains the purpose, query language, pagination, and response structure. No output schema exists, but the description adequately describes the return data.

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 meaning beyond schema: it provides concrete query examples, clarifies default and max values for _limit, and explains that omitting query lists all leads. 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 tool's function: 'Search or list leads (companies/accounts in Close) using Close's query language.' It specifies the resource (leads) and action (search/list), and distinguishes it from siblings like close_get_lead by focusing on listing/searching.

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 clear usage guidance: how to use query syntax with examples, how to list all leads by omitting query, and pagination with _limit and _skip. It does not explicitly mention when not to use it or alternatives, but the 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?

Annotations already indicate read-only, idempotent, and open-world. The description adds significant behavioral context: it pulls latest 10-K data with a post-Run-6 fix for correct fiscal year handling (including off-calendar fiscal years), and for drugs it pulls FAERS reports, approvals, and trials. It also mentions sorting by primary metric. 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 of about 150 words, efficiently front-loading the main purpose. It includes necessary technical details (e.g., the post-Run-6 fix) without being overly verbose. A slightly more structured format (e.g., bullet points for types) could improve readability, but it is 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 no output schema, the description provides minimal detail on return values ('paired data + pipeworx:// citation URIs per entity') and sorting. It does not explain the response format, pagination, error handling, or what happens if data is missing. For a tool with moderate complexity, more completeness would be beneficial.

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 some context beyond the schema by explaining what data each type pulls and giving concrete examples (tickers, CIKs, drug names). However, it largely repeats the schema's parameter descriptions without adding substantial new semantic meaning.

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 compares 2-5 companies or drugs side by side. It uses specific verbs ('Compare... side by side') and distinguishes itself from siblings like entity_profile (single entity) by focusing on multi-entity comparisons. The purpose is unambiguous and directly actionable.

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 usage scenarios: 'Compare X and Y', 'X vs Y', 'which is bigger', and rank-by-metric questions. It also notes it replaces 8-15 sequential lookups, implying efficiency. However, it does not explicitly state when not to use it (e.g., for single entity queries) or mention alternatives like entity_profile.

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 provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context: returns top-N tools with full schemas and examples, ready to call directly. No 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?

Description is a single, well-structured paragraph of 4 sentences. Front-loaded with core purpose, then examples and usage instruction. Efficient but could be slightly shorter.

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 simple parameters, the description is fully adequate: explains what it does, when to use, and what the response contains. No missing critical information.

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 what the schema already provides for parameters. It lists aliases but schema covers them.

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 domains (SEC filings, FDA drugs, etc.) and distinguishes from siblings by advising to call this FIRST to see the option set.

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 when you need to browse, search, look up, or discover what tools exist for...' and advises to call FIRST when many tools are available, implying when not to use (if tool is already known).

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 idempotentHint. The description goes beyond by detailing return fields (cik, company_name, recent_filings with URIs, fundamentals with notes on FY2025 numbers, patents API sunset with soft-fail, news fallback, LEI). It also explains the sort order and the two-number fix for revenues, which adds significant 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 quite long but every sentence provides unique and valuable information. It is front-loaded with the primary purpose. Minor room for structural improvement (e.g., bullet points) but overall 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 there is no output schema, the description thoroughly explains all return components, their sources, and limitations (e.g., patents sunset, fundamentals fix). It also covers input constraints and fallbacks, making the tool's behavior fully predictable.

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 meaning: it specifies that type should only be 'company' (noting other types coming soon), and for value it clarifies that tickers or zero-padded CIKs are accepted while names are not. This prevents incorrect invocations.

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 explicitly states it retrieves all information about a US public company in one call, and provides concrete use cases like 'tell me about X' or 'research Acme'. It distinguishes from calling multiple separate tools across SEC EDGAR, XBRL, USPTO, news, GLEIF, which directly addresses sibling differentiation.

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?

Clear guidance on when to use: when the user asks for company information that would otherwise require many tool calls. Explicitly states what not to use: names are not supported, and directs to resolve_entity first. Also specifies valid input formats (ticker or zero-padded CIK).

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 provide destructiveHint: true. The description reinforces this by stating 'Delete' and 'clear sensitive data', adding context on when to use it. 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?

Two tightly written sentences, no redundancy, and front-loaded with the core purpose. Every word contributes 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 the simple one-parameter tool with no output schema, the description covers purpose, usage context, and pairing. Could mention error behavior or outcome, but overall 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% and the parameter description is clear. The tool description does not add additional semantics beyond what the schema provides, 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?

The description clearly states the action ('Delete a previously stored memory by key') and resource, distinguishing it from sibling tools 'remember' and 'recall' by explicitly mentioning pairing. It is specific and actionable.

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 use cases (stale context, task done, clearing sensitive data) and suggests pairing with remember and recall. Lacks explicit when-not-to-use guidance, but given the simplicity, it is adequate.

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 indicate read-only, idempotent, non-destructive. Description adds process details: fetching page, extracting title/description/key links, and emitting standard markdown. 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 concise, front-loaded with main purpose, and each sentence adds value. 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?

No output schema, but description explicitly states output is a 'single text blob' for site-root/llms.txt. This provides sufficient expectation for the 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 covers 100% of parameters with descriptions. Description adds minimal extra meaning beyond schema, referencing 'key links' but not enriching parameter details. 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?

Description clearly states the tool generates an llms.txt file for AI crawlers, specifying the action (generate), resource (llms.txt), and target (any URL). It is distinct from sibling tools which focus on 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?

Description lists specific use cases: indexing client sites, drafting for own projects, auditing competitors. While it doesn't explicitly mention when not to use or alternatives, the use cases are clear and 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?

The description discloses rate limits (5 per identifier per day), that it is free, and that it does not count against the tool-call quota. Annotations provide 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 concise, well-structured, and front-loaded. Every sentence provides necessary 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 and lack of output schema, the description covers all essential aspects: purpose, usage, constraints, and expected content. It is complete for an agent to use 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%, but the description adds value by explaining the meaning of each enum type and providing guidance on how to write the message (specific, mention tools/packs, avoid end-user prompts).

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: to report bugs, request features/data, or give praise. It distinguishes from siblings by being the dedicated feedback mechanism.

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 specifies when to use each feedback type (bug, feature, data_gap, praise) and provides a constraint not to paste end-user prompts, giving clear guidance on appropriate 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?

Annotations already indicate safe read-only, idempotent, non-destructive behavior. Description adds valuable details: self-aggregating signal, derived from CF analytics-engine, no 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?

Four concise sentences, front-loaded with the core purpose, followed by bullet-like use cases and implementation details. 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 the tool's simplicity (one optional parameter, no output schema), the description covers all essential aspects: return values, time windows, use cases, data source, privacy, and caching. 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 covers 100% of parameters with descriptions. Description adds semantic insight: 'Shorter windows surface what's hot right now; longer windows show steady-state demand.' This enhances understanding 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?

Describes exactly what the tool returns (top tools, top packs, call volume) and specifies the time windows (24h, 7d, 30d). Provides three concrete use cases, clearly distinguishing it from siblings like ask_pipeworx or discover_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?

Explicitly lists three use cases: discovering hot data sources, confirming canonical tools, and seeing alignment with agent needs. Implies context but does not explicitly state when not to use or name 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?

Beyond annotations (readOnlyHint, openWorldHint, idempotentHint), the description adds rich behavioral details: two-mode mechanics, Jaccard similarity threshold (≥0.30), placeholder filtering (>20% placeholder fraction returns null), partition filter dropping specific slugs, response structure with fields like gap_pp, suggested_trade, and reasoning. 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 dense but well-structured with clear enumeration of modes, filters, and response fields. Every sentence adds value, though it could be slightly more concise. The use of caps for modes and semicolons aids readability, earning a 4.

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 complex two-mode arbitrage tool with no output schema, the description is remarkably complete. It details input parameters, internal logic (partition_check, Jaccard similarity, placeholder filtering), and output structure (opportunities array with gap_pp, suggested_trade, reasoning, etc.). No gaps remain for an agent to 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% (both parameters described in schema). The description adds semantics by explaining that 'event' expects a Polymarket event slug/URL for single-event mode and 'topic' expects a seed question for cross-event mode, with examples. This clarifies usage beyond schema types, meriting a 4 (baseline 3 due to 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 specifies the tool finds arbitrage opportunities on Polymarket using monotonicity violations and partition-sum checks, with two distinct modes (event and topic). It clearly distinguishes from sibling tools like polymarket_edges and polymarket_kalshi_spread by detailing its unique cross-event analysis and partition checks.

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 each mode (single event slug vs. topic seed question) and implies cross-event mode for catching date-range patterns. It lacks explicit 'when not to use' or comparisons to alternatives, but the context of sibling tools provides some guidance, and the modes are well-defined.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description goes beyond these by detailing the response structure (three segments under by_segment), the calculation details for each model family (e.g., lognormal barrier from FRED, GDELT ratio, favorite-longshot bias correction), and the inclusion of diagnostics so callers can see why segments might be empty. 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 fairly verbose but well-structured. It front-loads the purpose and then dives into technical details for each model family and parameter. Each sentence adds value, but the length might be reduced without losing clarity. The use of bullet-point-style formatting (with parentheses and dashes) helps readability.

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 (9 parameters, no output schema, multiple segments and models), the description is exceptionally complete. It explains the response top-level structure, the three opportunity segments, diagnostic fields, caching, and even caveats like the Fed bets exclusion. The description effectively compensates for the lack of an output schema by describing what the caller can expect.

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 all 9 parameters having descriptions. The description adds significant value beyond the schema, for example explaining why min_partition_leg_kelly exists (because min_kelly doesn't filter partition arbs since kelly_fraction_half=0 at parent level), and giving concrete defaults and usage context for each knob (e.g., slippage_pp: 'Bump for very thin partitions; drop to 0 if you have a smarter fill model').

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 function: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It is specific about the verb (scan, return), resource (Polymarket markets), and scope (Pipeworx data disagreements). The description also contextualizes its unique value by mentioning it is built for 'what should I bet on today' and distinguishes it from sibling tools like polymarket_arbitrage and polymarket_kalshi_spread.

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 the tool: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It also mentions caching behavior ('Cached 1h at the KV level keyed on all knobs') and provides parameters like min_liquidity and max_spread_pp to filter tradeable opportunities. However, it does not explicitly state when not to use this tool or provide direct comparisons to alternatives, which would strengthen the 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?

Adds substantial behavioral context beyond annotations: describes response structure, compatibility warnings, temporal alignment, and skipped-comparison counters. No contradiction with annotations (readOnlyHint, 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?

The description is somewhat lengthy but each sentence adds value. It is front-loaded with purpose and well-structured, though could be slightly trimmed without losing substance.

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 thoroughly explains the response structure and safety fields. Given the tool's complexity, it provides sufficient information for an agent 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 coverage is 100%, and the description adds meaning by detailing the two modes, pre-mapped topics, and override behavior. Provides additional context that enhances understanding 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 it computes cross-venue spreads between Kalshi and Polymarket for the same resolving question, and outlines two modes (`topic` and explicit). It differentiates from sibling tools, none of which appear to offer this functionality.

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 guidance on when to use each mode and explains safety fields that warn when spreads are not meaningful. Lacks an explicit statement of when not to use, but the safety mechanisms effectively serve that 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?

Annotations already declare readOnly, idempotent, non-destructive. Description adds value by clarifying scoping (identifier-based) and listing behavior, without contradicting 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?

Three concise sentences, front-loaded with core action, and no unnecessary 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?

Provides sufficient context for a simple retrieval tool, including scope and pairing. Slight gap: no mention of behavior when key is missing, but not critical.

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 context about the parameter's purpose and the effect of omitting it (list all keys), enhancing the agent's 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 uses specific verbs ('retrieve', 'list') and resources ('value', 'keys'), and distinguishes itself from siblings by pairing with '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?

Explicitly indicates when to use (look up stored context) and implicitly excludes alternatives by referencing sibling tools. Lacks explicit when-not-to-use, but context 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?

Describes parallel fan-out to multiple sources, fallback from GDELT to GNews on rate limits/5xx, USPTO soft-fail until reactivated, and return structure (grouped changes, total count, citation URIs). Annotations (readOnlyHint, idempotentHint) are consistent and description adds context 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?

Front-loaded with purpose and examples, then efficiently details sources, parameters, return format, and sibling tool reference. No redundant sentences; each sentence adds unique 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 tool complexity (multi-source parallel fan-out, fallback, soft-fail) and no output schema, the description fully covers behavior, parameter usage, and return structure. Completeness is high.

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?

Adds significant value beyond schema: explains `since` format with examples ('7d', '30d', '1y') and recommends typical monitoring values. Clarifies that `type` is limited to 'company'. Schema already has 100% coverage but description enriches it.

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 answers 'What's new with a company' and provides specific use examples ('what's happening with X', 'updates on Y'). It lists the sources (SEC EDGAR, GDELT/GNews, USPTO) and distinguishes from sibling 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 defines when to use: for news, updates, change-monitoring. Provides when-not-to-use: 'Use entity_profile instead when you want the static profile'. Also explains fallback behavior and parameter format recommendations.

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 behavioral context beyond the annotations, such as scoping by identifier, persistent memory for authenticated users, and 24-hour retention for anonymous sessions. The annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) are consistent with the description; 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 concise at roughly 80 words, front-loads the purpose, and provides all necessary information without fluff. 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?

For a simple tool with two parameters and no output schema, the description covers purpose, usage guidelines, behavioral traits, and parameter examples comprehensively. It is complete for an agent to understand when and how to use 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?

The input schema covers both parameters (key, value) with full descriptions and examples. The description does not add significant new information beyond what the schema provides, so a baseline score of 3 is appropriate given the 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's purpose: 'Save data the agent will need to reuse later — across this conversation or across sessions.' It identifies the specific verb (save) and resource (key-value pair) and distinguishes itself 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?

The description provides explicit guidance on when to use the tool: 'Use when you discover something worth carrying forward' and provides examples of what to store (tickers, addresses, preferences). It also mentions pairing with recall and forget for retrieval and deletion, though it 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?

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds that the tool 'cascades through several lookup endpoints internally,' which provides transparency beyond annotations. 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 purpose, usage, and type details. While it is relatively concise, it could be slightly more structured (e.g., bullet points for types) but still earns its sentences.

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 fully compensates by detailing expected return values for each entity type. It covers all 2 required parameters and their nuances. The tool's complexity (replacing manual lookups) is appropriately explained.

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?

Despite 100% schema coverage, the description adds significant meaning: it explains the return values for each type (e.g., 'returns ticker + 10-digit CIK + company_name' for company) and provides examples for the 'value' parameter. This enriches understanding 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's purpose: 'Resolve a user-spoken name to the canonical/official identifiers other tools require as input.' It specifically mentions converting names to IDs for 'company' and 'drug' types, which distinguishes it 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 includes explicit usage guidance: 'Use FIRST when you have a name but need an ID.' It also mentions that it replaces 2-3 manual lookups. However, it does not specify when not to use it or differentiate from alternatives like entity_profile, though the context 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?

Annotations already indicate read-only, open-world, idempotent, non-destructive. Description adds that it probes each entity with ai_visibility_check, returns ranked list with score, confidence, signal density. 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?

Two sentences, front-loaded with purpose, then method and output details, ending with a concrete example. No redundant or vague phrases.

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 (multi-entity, optional models, context, no output schema), the description adequately covers the use case, behavior, output fields, and decision guidance. It enables an agent to understand when to invoke and what to expect.

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%). Description adds value by noting that the first entity is treated as 'subject' for narrative, and that omitting 'models' defaults to workers-ai. This contextual guidance is beyond 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 it compares AI visibility across multiple entities, ranks them, and surfaces which is most/least recognized. It distinguishes from sibling tool 'ai_visibility_check' which is single-entity, and from generic 'compare_entities' by specifying context of AI presence.

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 'Useful for competitive AI-marketing audits' and provides an example question. It implies when to use this tool over alternatives by highlighting multi-entity comparison.

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, and destructiveHint. The description adds extra context: graceful degradation on partial failures, bundlephobia's first-time latency, and the sources_failed field. 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 concise yet comprehensive: 4 sentences covering purpose, usage, limitations, and output. It front-loads the core function and progressively adds detail 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 complexity (two APIs, partial failures, no output schema), the description fully covers return values, error handling, ecosystem constraints, and performance notes. No gaps identified.

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 both parameters. The description adds minimal extra but reinforces the context (e.g., scoped packages). Baseline 3 applies since schema fully covers parameter meaning.

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 performs a composite check for adding an npm package, specifying the two data sources (deps.dev and bundlephobia) and the exact use case. It distinguishes from siblings by focusing on npm ecosystem and providing actionable 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?

Explicitly tells when to use the tool (queries about safety, popularity, size) and when not to (other ecosystems) with an alternative (deps.dev:version). Also explains partial failures and latency expectations.

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 return format (verdict types, structured form, actual value with citation, percent delta) and scope limitations (v1 supports company-financial claims). Annotations already indicate read-only, idempotent, non-destructive behavior; description adds valuable 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?

Efficiently packs purpose, usage, scope, and output into a compact description. No redundant sentences; 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?

Covers purpose, usage, scope, and output format in the absence of an output schema. Could mention potential error cases or authentication, but overall sufficient for agent 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 has 100% description coverage for the single 'claim' parameter. Description adds usage examples and clarifies that it expects natural-language input, enhancing schema meaning.

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 fact-checks natural-language claims against authoritative sources, specifically for company-financial data via SEC EDGAR + XBRL. Distinguishes from sibling tools by its specialized validation 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?

Explicitly states when to use: 'when an agent needs to check whether something a user said is true' with examples. No explicit alternatives or exclusions, but context is clear.

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