Clinicaltables

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

Description adds value beyond annotations: explains free vs paid model, cost implications for BYO key, and return structure. No contradiction with annotations (readOnly, idempotent, openWorld).

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, each earning its place: purpose, default+api key behavior, and use cases. Front-loaded with verb and resource. No redundant information.

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

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

No output schema, but description explains return fields (score, confidence, signals, raw_response) and combined view. Covers entity disambiguation and pricing. Complete for a probe 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%, baseline 3. Description provides examples for entity, explains model options, clarifies _apiKey purpose and pass-through, and context disambiguates. Adds meaningful detail.

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 probes LLMs for brand visibility and scores it, with specific verb 'probe' and resource 'LLMs'. It distinguishes from sibling tools by focusing on AI visibility scoring, not just presence scanning.

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. Also explains default model and optional Anthropic probe. Lacks explicit when-not-to-use or alternative siblings, 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 readOnly, openWorld, idempotent. The description adds that it routes to 3,558 tools, fills arguments, and returns structured answers with stable citation URIs. This provides valuable 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?

The description is front-loaded with the key instruction ('PREFER OVER WEB SEARCH'), followed by systematic listing of use cases, trigger phrases, and examples. Every sentence adds information; no redundancy. Well-structured for quick comprehension.

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 as a meta-router and the absence of an output schema, the description adequately covers what the tool does, how it selects sources, and the nature of its response (structured answer with citations). It leaves no critical gaps for an agent to understand 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 coverage is 100% with clear descriptions for each alias parameter. The description adds value by listing example questions, helping agents formulate proper input. While not extensive, it compensates for the lack of additional parameter details.

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: 'PREFER OVER WEB SEARCH for questions about current or historical data' and lists specific domains (SEC filings, FDA data, etc.). It differentiates from web search and provides concrete examples, making the purpose unmistakable.

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 advises when to use this tool over web search and gives trigger phrases like 'what is', 'look up', 'find'. It also provides numerous examples of appropriate queries, leaving no ambiguity about usage context.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds significant behavioral context: returns structured refusal reasons, only uses tool result, costs extra LLM call, and specifies exact output fields. No contradictions. Fully transparent.

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

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

Description is moderately long but well-structured: begins with purpose, then mechanism, then output format, then usage guidelines. Every sentence adds value, though a bit verbose. Still highly effective and front-loaded with key 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 the absence of an output schema, the description compensates fully by detailing the exact return structure (fields, types, refusal reasons). It also covers behavioral nuances, error states, and cost implications. Completely addresses what an agent needs to use this tool correctly.

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

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

Schema coverage is 100% with all 6 parameters described as aliases for 'question'. Description does not add additional semantics or examples beyond what schema already provides. Baseline score of 3 is appropriate as the schema carries the load.

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 'Hallucination-resistant answer mode for high-stakes reads' and explains the mechanism (extracts answer using only tool result). It explicitly distinguishes from sibling 'ask_pipeworx' by mentioning same routing but grounded behavior. The purpose is specific and 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?

Provides explicit when to use: 'whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with examples. Also states when to prefer alternative: 'prefer ask_pipeworx for casual lookups' and mentions cost trade-off. Comprehensive and actionable.

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 mark the tool as readOnly, openWorld, idempotent, and non-destructive. The description adds extensive behavioral context: resolution confidence levels, parent_event extraction, news fallback handling, safety short-circuits for low-confidence matches, closed market handling, and wide-spread warnings. This far exceeds what annotations provide, giving a comprehensive understanding of tool behavior.

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

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

The description is well-structured with sections (purpose, use cases, classifiers, examples, response shapes), but it is lengthy, including elaborate fan-out examples that could be condensed. The front-loading is effective, but some sentences (e.g., detailed fan-out examples) could be more concise without losing essential 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 the tool's complexity (3 parameters, no output schema), the description thoroughly covers expected responses (market_match_confidence, parent_event, news fields, safety behaviors). It compensates for the lack of output schema by detailing response structures and edge cases, ensuring an agent can interpret outcomes correctly.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds context with examples (e.g., input formats) and explains the depth parameter, but does not provide additional meaning beyond what the schema already offers for each parameter. It does not detail parameter constraints or error conditions.

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: researching a Polymarket bet by pulling Pipeworx data. It specifies inputs (slug, URL, question) and outputs (evidence packet, comparison). However, it does not explicitly differentiate from sibling tools like polymarket_arbitrage or polymarket_edges, though the detailed use cases imply a distinct function.

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

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

The description provides explicit use cases ('should I bet on X', 'what does the data say about Y', 'is there edge in Z'), guiding when to use the tool. It lacks explicit 'when not to use' statements or references to alternative sibling tools, but the context is clear enough for an agent to decide.

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

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

Annotations declare readOnly, idempotent, openWorld, non-destructive. Description adds: data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), fiscal year handling, result sorting by primary metric, and citation URIs. 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?

Front-loaded with trigger phrases and key directive. The description is relatively long but each sentence adds information (data sources, handling of fiscal years, output format). Could be slightly trimmed but remains 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 (multiple entity types, data sources, sorting, citations), the description covers essential behavior. No output schema but mentions 'paired data + pipeworx:// citation URIs', which is sufficient for understanding return format. Strong guidance on when to use (always prefer over sequential lookups).

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 value by explaining what each type pulls (e.g., 'LATEST 10-K revenue + net income + cash + long-term debt') and provides concrete examples for values (tickers, drug names). This 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?

Description clearly states verb 'compare' with resource 'entities' (companies or drugs). Provides trigger phrases and explicitly distinguishes from sequential single-entity lookups, which are handled by siblings like entity_profile. High specificity.

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 (comparing 2–5 entities) and to prefer over sequential lookups. Provides example queries and enumerates use cases (which is bigger, better, etc.). No explicit when-not, 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 behavior. The description adds context by specifying the data source (NLM, ~700 conditions) and that results are 'patient-friendly' and return canonical names. 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, well-structured paragraph with three sentences that front-load the purpose, then provide context and examples. Every sentence earns its place, and there is no redundant text.

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

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

For a simple search tool with rich annotations and one required parameter, the description covers purpose, query formats, return values, and use cases. No output schema is needed as return values are clearly described as canonical names. It is fully complete for an AI 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?

With 100% schema coverage, baseline is 3. The description adds value by providing real-world usage patterns for the 'count' parameter (e.g., 'Use 1–3 for typeahead UX, 20–50 for browsing') and examples for 'terms', enhancing parameter 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?

The description clearly states it searches the NLM patient-friendly medical conditions vocabulary and returns canonical names, with specific query examples like 'What is [condition]' and use cases for symptom-to-condition lookup. It effectively differentiates from siblings like 'disease_names' by focusing on a lay-reader vocabulary.

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 use contexts (symptom-to-condition lookup, intake forms, simplifying clinical text) but does not explicitly contrast with alternatives like 'disease_names' or specify when not to use this tool. It is adequate for guiding 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=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds behavioral context: returns results 'ready to call directly, no second schema lookup needed' and mentions top-N relevance. This is valuable beyond annotations but does not contradict 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 a single paragraph that is front-loaded with the core purpose, followed by examples and usage guidance. Every sentence earns its place, and there is no unnecessary information. It is concise yet comprehensive.

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 6 parameters (with full schema coverage), no output schema, and the tool's complexity as a discovery mechanism, the description is complete. It explains the return format (top-N with schemas), usage context (call first), and provides examples. No gaps are evident.

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 parameters documented (query, limit, and aliases). The description does not add additional meaning beyond listing example queries and stating the default limit. Baseline 3 is appropriate since the schema already does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Find tools by describing the data or task.' It goes beyond a simple verb-noun phrase to specify that it returns top-N relevant tools with names, descriptions, and full input schemas, making it easy to understand what the tool does. It distinguishes itself from sibling tools by being a discovery meta-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 is provided: 'Call this FIRST when you have many tools available and want to see the option set.' This tells the agent when to use it (browsing/searching) and implicitly when not to (if the correct tool is already known). The description also lists example tasks like 'SEC filings, financials,' etc., giving context for valid use cases.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that it returns UMLS CUIs and canonical names and describes the search mechanism, providing useful 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?

The description is concise, combining usage examples and purpose in two sentences. It is front-loaded with examples and efficiently conveys the tool's utility.

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 purpose and 4 parameters, the description adequately covers what is returned and when to use it. However, it lacks details on pagination or ordering beyond the count parameter, which is partially covered in the schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does not add significant detail beyond the schema, except for an example query for 'terms'. No parameter meaning is overlooked.

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 searches the NLM Disease Names vocabulary for UMLS codes and canonical names. It provides multiple usage examples and explicitly distinguishes itself from the sibling tool 'conditions' by noting it is broader and includes rare diseases.

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 advises using the tool when 'clinical-grade vocabulary linkage' is needed rather than patient-friendly labels, implying a clear use case. However, it does not explicitly state when not to use it or provide alternatives beyond the sibling mention.

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 readOnly, openWorld, idempotent, and non-destructive. The description adds behavioral details: returns formatted names, matching is prefix/contains with AND tokens, and the `count` parameter range. 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 well-structured with a clear headline, examples, and parameter notes. While slightly verbose, each sentence adds value. It front-loads the purpose and key usage.

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 lookup tool without output schema, the description covers purpose, behavior, and parameter recommendations. It explains what returns look like (names with parenthetical forms). Could mention pagination or response format, but sufficiently 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?

All 4 parameters have schema descriptions (100% coverage). The description adds practical guidance: `count` suggests values for typeahead vs. browsing, `ef` lists specific extra fields, and `terms` explains matching logic. This goes 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 identifies the tool as a drug name lookup using RxTerms, with specific examples like 'Aspirin (Chewable)' and use cases for prescription entry and autocomplete. It distinguishes from sibling tools (e.g., conditions, disease_names) by focusing on drug names and RxNorm integration.

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?

It states when to use: 'prescription entry, drug name autocomplete, or as a stepping-stone to RxNorm RxCUI lookups.' It also advises on the `ef` parameter for including strengths. However, it does not explicitly exclude scenarios, but the context is clear enough.

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, openWorldHint=true. Description adds behavioral details: parallel fan-out, soft-fail for patents, and return 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 dense but front-loaded with examples and priority advice. It efficiently packs a lot of information in one paragraph. Some improvement could be made with bullet points, but 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?

Despite no output schema, the description lists all return fields (CIK, recent_filings with URIs, fundamentals, patents, news, LEI). It also covers input formats, limitations (patents sunset, name not supported), and prerequisites. Fully complete for agent decision-making.

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

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

Schema covers 100% of parameters with clear descriptions. Description adds contextual meaning: clarifies value accepts ticker or zero-padded CIK, and emphasizes names are not supported. This adds value 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's purpose: generate a full cross-source profile of a US public company in one parallel call. It distinguishes itself from sibling tools like resolve_entity (for name resolution) and chaining single-source lookups.

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 advises to prefer this tool over chaining SEC/XBRL/news lookups for holistic views. Also provides clear guidance: use ticker or CIK, not names; if only a name, use resolve_entity first. Limitations like patents API sunset are noted.

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 idempotentHint=true. The description adds context about specific use cases (clearing sensitive data) which is valuable beyond annotations. No contradiction detected.

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

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

Two sentences, front-loaded with the primary purpose. Nothing extraneous; every word earns its place.

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

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

For a simple tool with one required parameter and no output schema, the description is fully sufficient. It explains what the tool does, when to use it, and how it relates to siblings.

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 describes the 'key' parameter as 'Memory key to delete'. The description adds context that it's a 'previously stored memory' but does not significantly add meaning beyond the schema. Baseline score of 3 is appropriate.

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

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

The description clearly states the action 'Delete' and the resource 'previously stored memory by key'. It distinguishes itself from sibling tools by mentioning pairing with 'remember' and 'recall'.

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: 'Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier.' Also advises pairing with remember and recall.

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 that it fetches the page, extracts title/description/key links, and emits standard markdown format, providing 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?

Description is two sentences, front-loaded with the core purpose, and provides additional details efficiently with zero 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 no output schema, the description explains the output as a single text blob. It covers the main functionality and use cases. Missing error handling or edge case info, but still fairly complete for a simple 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?

Input schema has 100% descriptive coverage for both parameters. Description does not add new meaning beyond the schema, so baseline score of 3 is appropriate.

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

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

The description clearly states the tool generates an llms.txt file for a given URL, specifying the output format and use cases. It distinguishes itself from sibling tools which are unrelated.

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 explicitly lists use cases (getting client's site indexed, drafting for own project, auditing competitor). It does not mention when not to use or alternatives, but given no direct siblings, this 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 already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint. The description adds useful search behavior details (prefix/contains match, AND tokens, return format) 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?

The description is extremely concise, front-loaded with example queries, and efficiently conveys purpose, usage, and behavior in just two 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?

The description covers the main search behavior and return format. It could mention pagination via count or defaults for df/ef, but the schema covers these. Given good annotations, it is sufficiently 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?

With 100% schema coverage, the description adds little beyond the schema. The example for 'terms' is helpful, but 'df' and 'ef' are not clarified beyond schema. Baseline 3 is appropriate.

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

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

The description clearly states it is for searching ICD-10-CM diagnostic codes and gives explicit example queries and use cases (medical billing, EHR coding). It also distinguishes from the sibling icd9cm by name and 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?

The description provides clear use cases and example query patterns. It does not explicitly state when not to use or mention the sibling icd9cm, but the context is sufficient for an AI agent to understand when this tool is appropriate.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds only domain context ('US clinical records', 'pre-2015') and the phrase 'same shape as icd10cm' which hints at behavioral similarity but doesn't disclose additional traits.

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?

Extremely concise: two lines, front-loaded with alias and primary function, then usage guidance. Every sentence serves a clear 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?

Adequate for a search tool with open-world hint; domain context and sibling reference cover usage scope. Minor gap: no description of return format (though 'same shape as icd10cm' might imply, but icd10cm description not shown).

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

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

Input schema has 100% coverage with descriptions for all 4 parameters. Description adds no parameter-specific details beyond schema; 'same shape as icd10cm' is too vague to enhance semantics.

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

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

Clearly defines the tool as a searcher for legacy ICD-9-CM codes, explicitly distinguishes from icd10cm sibling via 'new claims must use icd10cm' and 'same shape as icd10cm'.

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 when-to-use ('pre-2015 US clinical records') and when-not-to-use ('new claims must use icd10cm') guidance, naming the 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 readOnlyHint, idempotentHint, and destructiveHint, so the description's behavioral disclosure is minimal. It adds the list of returned fields, which is useful but beyond the annotations' scope. 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?

Two sentences, front-loaded with the purpose, and no redundant words. The description is efficiently structured.

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

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

The tool is simple with one optional parameter and no output schema. The description lists all returned fields, and annotations are comprehensive. No gaps in context for an AI agent to use the tool correctly.

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

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

Schema coverage is 100% with a clear description for the only parameter 'include_inactive'. The description does not add additional 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 clearly states 'List the caller's active subscriptions' with a specific verb and resource. It also lists the returned fields, and distinguishes from siblings like 'subscribe' and 'unsubscribe'.

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 suggests when to use the tool: 'review what you're monitoring before adding more or to find an id to cancel'. This provides clear context, though it doesn't explicitly state when not to use it or name 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 convey read-only, idempotent, open-world behavior. Description adds no behavioral warnings beyond what annotations provide. It gives an example but doesn't disclose non-obvious traits.

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 three sentences, front-loaded with search patterns, no redundant words. Every sentence 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?

No output schema, but description gives an example output code. It doesn't detail result structure, but the example is sufficient for a simple search tool. Could mention that results include code and display name.

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

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

Schema covers all parameters (100% coverage). Description adds practical guidance: count parameter usage for typeahead vs browsing, example query for terms. This adds value 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?

Description clearly states the tool searches LOINC lab test codes, provides example search patterns and a concrete code example ("2093-3 Cholesterol"). It distinguishes from siblings (none of which are lab code lookups).

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 when normalizing lab results across institutions." This is clear context. No mention of when not to use, but sibling tools are distinct enough that exclusion is implied.

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. Description adds value by noting database size (~5M entries), search behavior (prefix/contains, whitespace-split), and return of NPI numbers plus names. 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?

Description is informative but presented as a run-on sentence with embedded examples. Could be better structured for quick scanning, though it covers key points.

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

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

No output schema, so description should explain return structure. It only states 'Returns NPI numbers + provider names'. Lacks detail on result format, pagination, or handling of large result sets. Adequate but not thorough.

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 extra context: 'terms' can be name fragment, NPI, or specialty; 'ef' can include address, specialty, gender (beyond schema). This enhances understanding 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 searches the NPPES registry for individual US healthcare providers, with examples of use cases. It distinguishes from sibling tools by specifying 'individual', but could be more explicit about the contrast with npi_organization.

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 provides example prompts and mentions search terms can be name, NPI, or specialty. It suggests using 'ef' for extra fields. However, no explicit when-not-to-use guidance or direct comparison with alternative tools like npi_organization.

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. Description adds context about the data source (NPPES registry with ~1.8M entries) and scope (hospitals, clinics, group practices). 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 concise, with two sentences plus example queries. It is front-loaded with the main purpose and includes relevant usage hints. Slightly redundant with example queries, but not overly verbose.

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

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

Covers purpose, data source, and parameter guidance. References sibling tool for shape. However, it omits any description of the return format or output fields, which is important given the lack of an output schema. Adequate for a simple search tool but leaves gaps.

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

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

Schema description coverage is 100%, establishing a baseline of 3. The description adds value for the 'terms' parameter by stating it can be organization name, NPI, or city, which goes beyond the schema's description of prefix/contains matching. Other parameters are not elaborated, but the added detail on the required parameter warrants a 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 the tool finds hospitals/clinics, looks up NPIs, and verifies facilities. It specifies the resource (NPPES NPI registry for organizations) and distinguishes from the sibling tool 'npi_individual' by noting 'Same shape as npi_individual'.

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 example queries (e.g., 'Find a hospital / clinic by name', 'look up NPI for [organization]') that guide when to use the tool. Mentions sibling tool 'npi_individual' for comparison, but lacks explicit when-not-to-use 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 indicate readOnlyHint=false and destructiveHint=false, but the description clarifies the tool submits feedback, is rate-limited (5 per identifier per day), and is free. This adds 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 5 sentences, front-loaded with purpose, then usage guidelines, then constraints. Every sentence adds value 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 feedback submission tool with no output schema, the description covers what it does, when to use it, how to format feedback, and constraints (rate limits, quota). It is complete and actionable 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% for 3 parameters, but the description adds meaning by explaining each type enum value (bug, feature, data_gap, praise, other) and clarifying the context object usage. It goes beyond repeating 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?

The description clearly states the tool's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It enumerates specific use cases (bug, feature, data_gap, praise) and distinguishes itself from sibling tools by being a 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 tells when to use the tool for each feedback type (bug, feature/data_gap, praise) and provides formatting guidance (describe in terms of tools/packs, avoid pasting user prompts). It also mentions rate limits and that it doesn't count against tool-call quota.

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, establishing safety. The description adds valuable context: data source ('CF analytics-engine'), privacy ('no PII'), and caching behavior ('5min-1h'). These details are 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?

The description is well-organized: core functionality first, then use cases, then data details. Every sentence is informative with no redundancy.

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

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

Despite lacking an output schema, the description explicitly states the output contains top tools, top packs, and call volume. This is sufficient for an agent to understand the tool's return value given its simplicity.

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

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

The input schema has 100% coverage with a description for the single parameter. The tool description adds extra rationale for window choices ('shorter windows surface what's hot right now'), enhancing 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 uses a clear verb ('returns') and specifies the resource ('top tools, top packs, total call volume'). It distinguishes from siblings like 'discover_tools' by focusing on trending usage from other agents.

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 lists three specific use cases for when to use this tool, providing clear guidance on application scenarios. However, it does not explicitly mention when not to use it 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 declare read-only, idempotent, open-world, non-destructive. The description adds substantial behavioral context: monotonicity checks, partition sum checks, similarity thresholds, placeholder filtering, and response structure. 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 verbose and contains many technical details that could be streamlined. However, it is well-organized with clear sections (REQUIRES, SEMANTIC ANCHOR, PARTITION FILTER) and front-loaded critical usage constraints.

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 details the response fields (opportunities, gap_pp, suggested_trade, etc.) and covers edge cases like placeholders and similarity. It addresses both modes thoroughly, making it complete for a tool with two parameters and no required arguments.

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 already describes both parameters with 100% coverage. The description adds meaning by explaining the behavioral differences between event and topic modes, giving example values, and clarifying the impact on output. This goes beyond the schema definitions.

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 via monotonicity violations and partition-sum checks, distinguishing event and topic modes. The verb 'Find' and resource 'arbitrage opportunities on Polymarket' are specific, and it differentiates from siblings 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?

Explicitly says REQUIRES event or topic, recommends which mode for which scenario, and provides examples. Lacks explicit exclusions or alternatives relative to sibling tools, but context is clear enough.

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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description expands with model details, caching (1h), diagnostics, and edge evaluation, adding significant value beyond annotations 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?

The description is dense but well-structured, front-loading purpose and segmenting details. Every sentence is valuable, though it could be slightly more concise for 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 9 parameters and no output schema, the description covers return structure (by_segment, diagnostics), caching, and knob effects thoroughly. It leaves no critical gaps for agent decision-making.

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

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

Schema coverage is 100% with each parameter having a description. The description adds usage context for knobs like min_partition_leg_kelly and tradeable-edge filters, 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 states it scans Polymarket markets to return opportunities where Pipeworx data disagrees with market price. It provides specific model families and segments, distinguishing 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 says 'Built for "what should I bet on today"' and explains when to use knobs like min_liquidity and max_spread_pp. It lacks explicit when-not to use this vs. siblings, but the specificity implies its niche.

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 many behavioral traits: read-only (consistent with annotations), response structure (leg-by-leg prices, spread in percentage points), safety fields (compatibility_warning with two cases, temporal_alignment), and counters for skipped comparisons. 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 long but well-structured with sections for modes, response, and safety fields. Every sentence adds value given tool complexity, but could be slightly more concise. Still, it is front-loaded with core purpose and clear headings.

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 thoroughly explains response fields (leg prices, spread, compatibility_warning, temporal_alignment, skipped counters). Covers edge cases and behavioral nuances, making the tool understandable without external documentation.

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 meaning beyond the schema: explains topic is pre-mapped with 10 shortcuts (listed), and explicit parameters override topic mapping. Schema already has 100% coverage, but description gives operational context and examples.

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 computes cross-venue spreads between Kalshi and Polymarket for the same resolving question. It specifies two modes (topic shortcuts and explicit pairings) and distinguishes from sibling tools by focusing on cross-venue comparison.

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 when-to-use guidance: two modes (topic shortcuts or explicit tickers), and warns when spreads are not meaningful via compatibility_warning and temporal_alignment. It even notes that most pre-mapped topics return warnings, setting realistic 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?

Annotations already indicate read-only, idempotent, and non-destructive traits. The description adds context about the data source (NLM curated, ~7k entries) and output format (short names). 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?

Concise, front-loaded with example queries, and efficiently communicates purpose, usage, and alternatives in a single paragraph.

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 simple nature and good annotations, the description fully addresses what it does, when to use it, and what it returns. No output schema needed.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds high-level usage context (e.g., typeahead UX) but does not detail individual parameters 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 as searching clinical procedure names from NLM curated data, providing patient-friendly names. It uses specific verbs like 'search' and 'returns' and distinguishes itself from billing code tools like icd10cm.

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 advises when to use ('for forms or intake screens') and when not to ('for billing codes use icd10cm or a CPT source instead'), providing clear 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 indicate read-only, idempotent, non-destructive behavior. The description adds scoping details ('Scoped to your identifier') and the dual behavior (retrieve with key, list all without). No contradictions. It lacks details about missing keys or return format, but overall adds value 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 three sentences long, each serving a distinct purpose: the first states the action, the second explains when to use it, and the third covers scoping and pairing. No redundant or verbose content.

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

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

Given the tool's simplicity (single optional parameter, no output schema) and the rich annotations, the description covers all necessary context: purpose, usage, scoping, and relationships with siblings. It is complete for an AI 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 only parameter has a clear description in the schema. The description does not add further meaning beyond what the schema already provides, so baseline score 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 explicitly states the action: 'Retrieve a value previously saved via remember, or list all saved keys (omit the key argument).' It clearly identifies the resource as saved memory values, and distinguishes from sibling tools like 'remember' and 'forget' by positioning itself as the retrieval counterpart.

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 context: 'Use to look up context the agent stored earlier... without re-deriving it from scratch.' It mentions pairing with remember and forget. However, it does not explicitly state when not to use this tool or mention alternative approaches, leaving a minor gap.

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 goes beyond annotations by detailing that each alert carries source, citation_uri, and raw payload, and explains the mark_read behavior affecting subsequent calls. It aligns with readOnlyHint and idempotentHint.

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, filtering, mark_read, and alternative access. Every sentence adds value, no redundant information.

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

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

Despite lacking an output schema, the description covers return structure (source, citation_uri, raw payload) and usage context (polling, REST endpoint). For a read operation with 5 optional params, this is thorough.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the effect of mark_read and suggesting polling, and provides example filter type 'sec_8k', making parameters more actionable.

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 pulls fired events from the subscription feed, with specific verb and resource. It distinguishes from sibling tools like list_subscriptions and recent_changes by focusing on alert retrieval.

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

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

The description mentions polling is fine and provides an alternative REST endpoint, giving context on when to use this tool vs scripts/dashboards. However, it does not explicitly exclude other sibling tools like recent_changes.

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 and idempotentHint=true. The description adds valuable behavioral details: fallback mechanisms (GDELT→GNews), USPTO soft-failure, and structured return format. 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 example queries, then details, making it scannable. It is slightly lengthy but every sentence adds value.

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

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

Given no output schema, the description explains the return structure (changes grouped by source, total_changes count, citation URIs). It also covers multiple data sources and failure modes, making it sufficiently complete for a complex tool.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema: 'since' accepts ISO dates or relative shorthand (e.g., '7d', '30d'), and 'value' accepts ticker or zero-padded CIK. This aids agent understanding.

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

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

The description clearly states it is a change feed for a company, fanning out to multiple sources (SEC, GDELT/GNews, USPTO). It distinguishes from the sibling tool 'entity_profile' by explicitly noting when to use that instead.

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 when-to-use guidance via examples ('What's new with X', 'latest on Y') and contrasts with 'entity_profile' for static profiles. However, it does not explicitly state when not to use this 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?

The description adds behavioral context beyond annotations: it explains scope (by identifier), persistence (24 hours for anonymous, permanent for authenticated), and that idempotentHint=true. 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 three sentences, front-loaded with the purpose, and contains no redundant information. Every sentence contributes useful context.

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

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

For a simple key-value storage tool with no output schema, the description covers how to use it, what to store, scope, and persistence. It is complete for its complexity.

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

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

Schema description coverage is 100% with detailed descriptions for key and value. The description adds context by providing examples (e.g., 'subject_property', 'target_ticker') and explaining how values are used (findings, addresses, preferences). This adds value 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 'Save data the agent will need to reuse later', specifying the action (save) and resource (data). It distinguishes from sibling tools 'recall' and 'forget' by explicitly mentioning them as complementary 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?

It provides explicit guidance: 'Use when you discover something worth carrying forward...' and details the scope (key-value pair scoped by identifier) and persistence differences between authenticated and anonymous sessions. It also suggests pairing with recall and forget.

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 readOnly, openWorld, idempotent, non-destructive. Beyond that, the description adds that each call internally cascades through several endpoints, returns citation URIs, and auto-disambiguates company names. This provides valuable behavioral context not captured in 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 well-structured with example phrases, a clear mission statement, and bullet-like details for each supported type. It is slightly verbose with the internal cascading mention but still 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?

No output schema, so the description must explain return values. It does so thoroughly for both entity types, including the citation URIs. Input formats and auto-disambiguation are also covered. The tool has moderate complexity with two parameter types, and the description fully addresses it.

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 both parameters with descriptions. The description adds concrete examples ('AAPL', 'ozempic') and explains what each parameter returns (e.g., company: ticker + CIK + company_name + citation). This enriches the 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?

The description starts with concrete examples ('ticker for...', 'CIK for...') and explicitly states the tool resolves user-spoken names to canonical IDs. It clearly distinguishes from sibling tools by emphasizing ID resolution as a first step, whereas siblings like 'entity_profile' or 'compare_entities' likely require IDs.

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 FIRST whenever you have a name but need an ID', providing clear guidance. It also mentions that internal cascading replaces 2-3 manual lookups, implying efficiency. However, it does not explicitly state when not to use it or name alternative tools for other scenarios.

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 (readOnlyHint, idempotentHint, etc.) indicate safe, read-only behavior, and the description adds rich context: it reveals the tool internally calls ai_visibility_check, ranks results, and returns confidence and signal density. 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 four sentences, tightly packed with essential information: purpose, process, use case, and output format. No extraneous words; ideal front-loading.

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 explicitly states the return format (ranked list with score, confidence, signal density). Combined with clear parameter docs, the tool is well-specified 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 covers all four parameters with clear descriptions, and the description adds extra meaning: the first entity is treated as the subject, and _apiKey is only needed if 'anthropic' is in models. This goes beyond what the schema alone provides.

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 (compare, probes, ranks) and clearly identifies the resource (AI visibility across multiple entities). It distinguishes from sibling ai_visibility_check by emphasizing side-by-side comparison and ranking, making its unique purpose unmistakable.

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 frames the tool as useful for 'competitive AI-marketing audits' and provides an example question. While it implies when to use it, it does not explicitly state when not to use it or name alternatives beyond the implicit contrast with ai_visibility_check.

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, non-destructive. Description adds extra context: fans out across two external sources, returns summary block with 11 fields, per-advisory detail, links, alternative versions. Notably warns that bundlephobia's first measurement can take 5-30s and that partial failures are handled gracefully via sources_failed field. 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?

Description is fairly long but front-loaded with key purpose. Every sentence adds value, explaining composite nature, use cases, return fields, limitations, and error handling. Minor verbosity but overall well-structured.

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

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

Given complexity (multiple sources, partial failures, specific fields) and no output schema, the description thoroughly covers what the tool returns (summary block, per-advisory, links, alternative versions), behavioral details (timeout, graceful degradation), and ecosystem scope. Complete for effective use.

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

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

Schema description coverage is 100%, so baseline is 3. Description mentions defaults (version defaults to latest) and scoped packages, but this is already in schema. Adds minimal extra 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 is a composite check for npm packages, combining deps.dev and bundlephobia data to answer questions about safety, popularity, and size. It distinguishes itself from sibling tools like scan_competitor_ai_presence by focusing on package metadata.

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 asks 'is X safe / popular / small' or 'what does adding lodash cost me'. Also notes ecosystem limitations (NPM only in v1) and partial failure handling, providing clear context for choosing this tool over 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?

Beyond annotations (readOnlyHint, idempotentHint), the description reveals embedding model (BGE-base-en), chunking strategy (overlapping 500-char windows), input cap (200K chars with truncation flag), and output specifics (passages with offsets and scores). This 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?

Two sentences, front-loaded with the core action, no redundancy. Every clause adds value.

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

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

Given the absence of an output schema, the description adequately explains the return format. It covers key behavioral details (embedding, windowing, cap) and differentiates from 30+ sibling tools 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 covers 100% of parameters, so baseline is 3. The description adds context on how parameters are used (e.g., truncation for text, query as natural language) beyond their schema descriptions, justifying a score of 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 performs semantic search inside a fetched record, specifying the verb 'search' and resource 'within a source'. It distinguishes itself from sibling tools like ask_pipeworx_grounded by describing how they pair together.

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 advises using the tool when the record is too large for the prompt, and mentions pairing with ask_pipeworx_grounded. However, it does not explicitly state when not to use it or compare with other sibling tools beyond that.

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 rich behavioral context beyond annotations: requires OAuth, details on each subscription type with examples, delivery constraints (SMS cap, phone verification), and caveats for patent_grant type. Discloses non-obvious behavior clearly.

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: opening sentence defines purpose, then requirements, type details, delivery options. Uses examples and bullet-like formatting. No unnecessary words; front-loaded with key 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?

Thorough for a complex tool with 3 params, nested objects, and 4 enum types. Covers all types with parameters, delivery options with constraints, and return value. No output schema needed as return is simple.

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 significant value: explains each type with examples and parameters, provides constraints for delivery (SMS cap, email validation). Exceeds what schema alone provides.

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 'Create a proactive monitoring subscription to a live-data event stream' with a specific verb and resource. Distinguishes from siblings like 'unsubscribe' and 'list_subscriptions' by focusing on creation and monitoring. Also notes return value.

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 when-to-use guidance: requires Pipeworx OAuth account, lists supported types and delivery channels. Implicitly suggests when not to use (no OAuth) but does not explicitly contrast with sibling tools like 'recent_alerts' for pull vs push.

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, and idempotentHint. The description adds behavioral details: it performs prefix/contains matching, whitespace-splits into AND tokens, and returns codes like 'mg/dL' and '[in_i]'. This additional context about query behavior and output examples goes beyond the structured 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 relatively short and front-loaded with the purpose. However, the initial placeholder format '[X]' and '[Y]' is ambiguous and wastes space. The rest is clear and 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?

With no output schema, the description compensates by giving output examples. The search behavior is explained, and all parameters are documented. Given the tool's simplicity and the rich annotations, the description provides sufficient context for correct invocation.

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

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

Schema coverage is 100%, and each parameter has a description. The tool description provides an example query ('mg/dL') but does not elaborate on the meaning of 'df' or 'ef' beyond what the schema says. Baseline of 3 is appropriate as the description adds minimal value over 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 that the tool searches UCUM for unit of measure codes, with examples like 'mg/dL' and '[in_i]'. It distinguishes itself from siblings by specifying it handles unit codes used in health-IT systems, and includes a use case of normalizing lab results or rendering measurements.

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 normalizing lab result units or rendering measurements,' providing clear context for when to invoke the tool. However, it does not mention when not to use it or alternatives among the many sibling tools, missing a chance for exclusions.

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 key behavioral traits (ownership check, soft deactivation) beyond annotations, which already indicate non-destructive but mutable behavior. 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?

Three concise sentences, front-loaded with the core action, no extraneous information.

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

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

Complete for a simple tool with one parameter and no output schema—covers purpose, constraints, and side effects.

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 'id' is fully described in the schema with origin information ('returned by subscribe'). Description adds no extra param detail but is sufficient given 100% 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 action ('Cancel a subscription by id') and resource (subscription), distinguishing it from sibling tools like 'subscribe' and 'list_subscriptions'.

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 specifies ownership enforcement ('you can only cancel your own subscriptions') and describes what happens to the row ('deactivated, not deleted'), guiding when and how to use.

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

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

Annotations declare readOnly, openWorld, idempotent, non-destructive. Description adds return format (verdict types, structured form, citation, delta), data source (SEC EDGAR + XBRL), and scope. No contradiction; augments annotations well.

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 comprehensive yet reasonably concise. Front-loaded with purpose and usage, followed by details. Could trim some example phrasings, 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?

Covers all essential aspects: purpose, usage, input, output, domain, data source, and efficiency. No output schema, but description sufficiently explains return values. Differentiates well from 20+ siblings.

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?

Single 'claim' parameter with clear schema description (examples provided). Tool description reinforces with natural-language phrasing but does not add substantial beyond schema. Schema coverage is 100%, baseline 3; examples push to 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?

Description clearly states the tool performs natural-language claim verification against authoritative sources, with explicit mention of domain (company-financial claims) and example phrasings. It distinguishes from siblings like 'compare_entities' or 'entity_profile' by being dedicated to fact-checking.

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: 'Use whenever the agent needs to check whether something a user said is factually correct.' Also notes limitations (v1 supports company-financial claims) and efficiency benefit (replaces 4-6 sequential calls).

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