Simap

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

Beyond annotations (readOnlyHint, idempotentHint), the description adds cost/API key requirements for Anthropic, the default model, and return structure. Does not mention rate limits or error behavior, but annotations already cover safety.

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

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

Four sentences, each serving a distinct purpose: purpose+scoring, default+api key, return format, use cases. Zero wasted words; information density is high and front-loaded.

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

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

Despite no output schema, describes per-model return fields (score, confidence, signals, raw_response) and combined view. Covers all 4 parameters with examples. Adequately complete for a probe tool with moderate complexity.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by clarifying default behavior for 'models', the role of '_apiKey' (pass-through to Anthropic), and disambiguation for 'entity' and 'context' with 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 uses a specific verb ('probe'), resource ('LLMs'), and outcome ('score visibility 0-100 per model'). It clearly distinguishes from siblings like 'scan_competitor_ai_presence' by emphasizing per-model scoring and default model behavior.

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

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

Explicitly lists use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains when to use the free default vs. paid Anthropic probe. Lacks exclusions or alternatives beyond the implicit sibling differentiation.

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

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

Annotations already cover read-only, open-world, and idempotent behavior. The description adds useful context beyond annotations: it routes across thousands of verified sources, returns structured answers with stable pipeworx:// citation URIs, and notes it is 'one fast call'. It does not discuss error handling or empty results, but for a read-only lookup tool this is sufficient.

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 longer than ideal but front-loaded with the key directive and every sentence carries purpose. The enumeration of example queries and source domains is somewhat dense, but it directly informs invocation. It is appropriately sized for a broad routing tool.

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

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

Despite having no output schema, the description clearly states the return format (structured answer with citation URIs), scope (current/historical data across many domains), usage priority, alternative escalation paths, and operational characteristics (works on every tier, one fast call). For a general-purpose entry-point tool, this is highly complete.

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

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

Schema coverage is 100% and the parameter descriptions already explain that the question accepts aliases. The description adds no new parameter-specific semantics; it only generically says 'fills arguments'. The baseline of 3 applies because the schema fully documents the natural-language 'question' parameter.

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

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

The description uses a specific action—'routes the question to the right one of 5,462 tools... returns the structured answer with citations'—and clearly differentiates itself from siblings like ask_pipeworx_grounded and deep_research. It states exactly what the tool does and for what kind of queries.

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?

Usage guidance is explicit and actionable: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', and 'Step up only when needed' names the specific alternatives (ask_pipeworx_grounded, deep_research). It even gives trigger phrases and examples, leaving little ambiguity about when to pick 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 substantial context beyond annotations: it explains the beta nature, that candidate routing improvements are enabled live when under test, that currently no candidate is active (so it matches ask_pipeworx exactly), and that results are compared against the stable router. It also clarifies 'Falls back to nothing' meaning it's a full router. 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, each conveying critical information: what the beta is, current state (no active candidate), and usage guidance. It is front-loaded with the most important detail and avoids redundancy, making it concise and well-structured.

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

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

Given the tool's complexity as a universal router with thousands of tools, the description provides sufficient context: it explains the beta status, current identity, how to use it, and what happens with routing improvements. The mention of 'same response shape' compensates for the lack of an output schema, making it complete for the agent.

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

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

The input schema provides 100% coverage with descriptions for all 6 parameters, including aliases for 'question'. The description adds no extra parameter semantics beyond noting 'same arguments' as ask_pipeworx, but the schema already covers the meaning well. 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 this is the beta version of ask_pipeworx, a universal router with the same 5,462 tools and same arguments. It distinguishes itself from the stable ask_pipeworx by explicitly noting it's the experimental edge with candidate routing improvements. The verb 'ask' is implied in the name but the description elaborates its role as a router.

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

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

The description gives explicit guidance on when to use it: 'Use it exactly like ask_pipeworx when you want the newest routing.' It also clarifies that it's a full working router, not a stub. However, it doesn't explicitly state when not to use it or name alternative tools beyond referencing ask_pipeworx, so it falls slightly short of full exclusion 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?

Beyond the readOnly/idempotent annotations, the description discloses the full pipeline (routing, fetching, extracting), the structured success and refusal response including refusal_reason enum values, and the cost of one extra LLM call. This goes far 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?

Though lengthy, every sentence earns its place: purpose, behavior, response format, use cases, and cost. The dash-separated clause structure keeps it readable and front-loaded with the core idea.

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 fully documents the return shape, including success fields and refusal reasons. It also covers prerequisites (high-stakes use), alternatives, and operational trade-offs, making it complete for the tool's complexity.

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

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

Schema description coverage is 100% and the schema already explains the aliases. The description adds no additional parameter-specific meaning, so the baseline of 3 applies.

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

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

The description immediately states the tool is a 'Hallucination-resistant answer mode for high-stakes reads' and explicitly contrasts it with the sibling ask_pipeworx by describing the extraction-only-from-data behavior. The verb+resource+scope is specific and distinct.

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 explicitly states when to use ('whenever an answer will be quoted, cited, or acted on') and when not to ('prefer ask_pipeworx for casual lookups'), also naming the alternative. This is the clearest possible 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 set readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description goes far beyond: it details fan-out behavior, resolver contract, parent event extraction, news fallback mechanisms, safety short-circuits, closed market handling, wide-spread liquidity warnings, and resolution-rule risk parsing. There is no contradiction.

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

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

The description is long but well-structured with clear sections (CLASSIFIERS, FAN-OUT EXAMPLES, RESPONSE SHAPES, etc.). Every sentence provides necessary detail. While not concise, it earns its length by covering many relevant scenarios and edge cases.

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

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

Given the complexity of the tool (multiple fan-out routes, response shapes, safety mechanisms), the description is remarkably complete. It explains return values in detail, even without an output schema. It covers resolver confidence, parent events, news fallback, market closure, liquidity, and cancellation rules.

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 three parameters adequately described (market, depth, include_raw). The tool description enriches these by explaining how they affect behavior (e.g., depth determines fan-out scope, include_raw controls response size). This adds marginal 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 the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies the verb (research/bet), the resource (Polymarket bet using Pipeworx data), and distinguishes itself from sibling tools like polymarket_arbitrage and polymarket_edges by focusing on research and data collection rather than arbitrage or edge detection.

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 for "should I bet on X", "what does the data say about Y", or "is there edge in Z".' This provides clear guidance. It does not explicitly state when not to use, but the sibling tools cover alternative use cases. The context is strong 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 indicate readOnly, openWorld, idempotent, non-destructive. Description adds details: data sources (SEC EDGAR/XBRL, FAERS), correct handling of fiscal years, sorting by 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?

The description is a single paragraph with front-loaded trigger phrases. It is dense but efficient, covering all key aspects without unnecessary words.

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

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

No output schema, but description explains return format (paired data + citation URIs). It covers entity types, value constraints, data sources, and sorting, making it sufficient for an agent to understand the tool's behavior.

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

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

Schema covers 100% of parameters with descriptions. Description adds meaning: explains what data each type pulls, limits on values (2-5), and that results are sorted by primary metric.

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 like 'compare' and 'side-by-side comparison' with clear resources: companies (SEC EDGAR financials) and drugs (FAERS data). It distinguishes from sibling tools like entity_profile and validates against sequential 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?

The description explicitly states 'ALWAYS PREFER over sequential single-pack lookups' and provides trigger phrases. While it doesn't specify when to avoid usage, the scope is well-defined.

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

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

Despite readOnly/openWorld/idempotent annotations, the description adds substantial behavioral context: account/payment requirements, parallel decomposition, return packet structure (evidence, confidence, source, fetched_at, pipeworx:// citation), gaps[] never invented, contradictions[] for standard/thorough, semantic excerpting of large records, and expected latency (15-90s). 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 long but front-loaded with the critical account requirement and structured logically: purpose, use cases, exclusions, depth semantics, return format. Some redundancy (e.g., mentions of facet decomposition appear twice), but each sentence contributes essential behavioral detail for a complex tool.

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 high complexity and absence of an output schema, the description is remarkably complete: it covers prerequisites, return types (findings packet, gaps[], contradictions[], hop field, citation_uri), error/edge behavior (empty gaps for non-catalog topics), performance expectations, and how citations are guaranteed fetchable. Everything needed to set expectations is present.

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 enriches both parameters: it explains what 'depth' values mean (quick=3 facets, standard=5 + gap recovery, thorough=8 paid + iterative hop) and clarifies that 'question' can be broad/multi-part since decomposition is the point. This adds meaningful context 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: 'Grounded multi-source research across Pipeworx's 1419 STRUCTURED data sources' in ONE call, decomposing questions into facets and routing to 5,462 tools in parallel. This specific verb+resource+scope distinguishes it from siblings like ask_pipeworx and bet_research.

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 when-to-use guidance: 'For a single lookup use ask_pipeworx', 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx', and 'If you are not signed in, use ask_pipeworx instead'. Also explains depth-level trade-offs (standard vs thorough) for multi-step questions.

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 and idempotent behavior. The description adds valuable detail about returning full schemas with curated examples, ready to call directly, without contradicting annotations.

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

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

Three sentences front-loaded with purpose, followed by domain examples, return details, and usage guidance. Efficient and well-structured.

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

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

Covers purpose, usage context, and return details well. Lacks discussion of error cases or edge conditions, but adequate for a discovery tool with 6 parameters and no output 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% with all 6 parameters described (including aliases). The description adds no new semantic detail beyond reiterating the query purpose, so baseline score applies.

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

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

The description clearly states the tool finds tools by describing data or task, enumerates many domains, and explicitly distinguishes itself as a first-step browsing tool, setting it apart from siblings that perform specific tasks.

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 'Call this FIRST when you have many tools available and want to see the option set (not just one answer)', providing clear when-to-use and implicit 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 already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context: it fans out across multiple sources, mentions a soft-fail for patents due to USPTO sunset, and describes the return structure. This goes beyond the annotations, scoring a 4.

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

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

The description is detailed and front-loaded with example queries and the 'ALWAYS PREFER' guidance. However, it mixes examples, return structure, and technical notes in a single dense paragraph, which could be slightly more structured. Still, every sentence adds value, earning a 4.

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

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

Given the tool's complexity, high schema coverage, and absence of an output schema, the description covers the return fields, constraints (e.g., patent sunset, name unsupported), and context clearly. It is sufficiently complete for an agent to understand what the tool does and what to expect.

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

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

Schema coverage is 100%, so the schema already documents both parameters. The description adds meaning by stating that type only supports 'company', value can be ticker or CIK, and names are not supported. This additional context justifies 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 provides a 'full cross-source profile of a US public company' and lists specific data sources (SEC, XBRL, USPTO, news, GLEIF) and return fields. It distinguishes itself from chaining single-pack lookups by stating 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups' when the user asks for a holistic view.

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 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also states that names are not supported and advises to 'use resolve_entity first if you only have a name,' providing clear guidance on when to use this tool vs. 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 provide destructiveHint=true, so the description's job is lighter. It adds context on why to delete (stale context, task done, sensitive data) 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?

Two concise sentences, first defining purpose, second providing usage guidance. 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?

For a simple one-parameter tool, the description covers purpose and usage. It could mention return behavior or edge cases, but overall sufficient.

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

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

Schema covers 100% of parameters with a clear description for 'key'. The tool description adds no additional parameter information beyond the schema, achieving the baseline.

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 'Delete a previously stored memory by key', providing a specific verb and resource. It distinguishes itself from sibling tools like 'remember' (store) and 'recall' (retrieve).

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

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

Provides explicit use cases: 'when context is stale, the task is done, or you want to clear sensitive data'. Also references sibling tools 'remember and recall' as 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, open-world, idempotent, non-destructive. Description adds behavioral details: fetches page, extracts title/description/key links, emits standard markdown. No contradiction.

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

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

Three sentences, each earning its place: main action, process, use cases. Front-loaded and no fluff.

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

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

Given simple tool with 2 params and no output schema, description covers input, process, output format, and use cases adequately. Annotations handle safety and idempotency.

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 both parameters. The description does not add significant extra meaning beyond what schema already 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?

Description specifies verb 'generate', resource 'llms.txt', and target 'any URL'. Clearly distinguishes from siblings by focusing on llms.txt generation, not general AI visibility scanning or research.

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

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

Explicit use cases provided: indexing client's site, drafting for own project, auditing competitor. Does not mention when to avoid or alternatives, 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 already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by specifying the caller's subscriptions and the exact fields returned, which complements the annotations without contradicting 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?

Two sentences, no wasted words. The first sentence states the purpose and return fields; the second provides usage context. Perfectly concise and well-structured.

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

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

With rich annotations and a fully described schema, the description covers all essential aspects: what the tool does, what it returns, and when to use it. No gaps exist.

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 the single parameter (include_inactive), with a clear description in the schema. The tool description does not add additional parameter context, so the 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 verb 'list' and the resource 'subscriptions', specifies that it returns the caller's active subscriptions, and lists the returned fields. This distinguishes it from sibling tools 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?

Provides specific when-to-use guidance: 'review what you're monitoring before adding more or to find an id to cancel'. While it doesn't explicitly state when not to use it or name alternative tools, the context is clear.

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

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

Beyond the annotations (all false), the description discloses rate limiting ('Rate-limited to 5 per identifier per day'), quota exemption ('Free; doesn't count against your tool-call quota'), and the human process ('The team reads digests daily and signal directly affects roadmap'). It also sets content policy by instructing not to paste the end-user's prompt. These are meaningful behavioral traits 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 longer than average but every sentence carries information: purpose, use cases, exclusions, content guidance, and operational details. It front-loads the primary purpose and then logically sequences exclusions and constraints. It is efficient for the amount of guidance provided, though it could be slightly tightened.

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 completely covers the tool's purpose, use cases, exclusions, content guidelines, rate limits, quota behavior, and impact on roadmap. There is no output schema, but for a feedback tool the response is likely a confirmation; the description adequately sets expectations. Given the moderate complexity and full schema coverage, the description is fully sufficient.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by instructing users to 'Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt,' which clarifies the intended content of the 'message' parameter beyond the schema. It also implicitly guides the context object by mentioning 'which tool, pack, or vertical.' This justified 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 opens with a specific verb+resource: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It clearly distinguishes this from sibling tools by positioning it as a feedback channel for Pipeworx itself, contrasting with research/query tools like ask_pipeworx and deep_research. The scope limitation to 'tools served by this Pipeworx connection' further differentiates it from external MCP tools.

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

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

The description gives explicit when-to-use criteria for each feedback type: 'Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise).' It also provides a when-not-to-use condition: if the tool came from a different MCP server, file it with that server. This is exemplary usage 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?

The description adds valuable behavioral details beyond annotations: it discloses the data source (CF analytics-engine), privacy (no PII), caching behavior (5min-1h), and the self-aggregating nature. This exceeds 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 concise with three sentences front-loading the output and then listing use cases. No redundant or extraneous information; every sentence earns its place.

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

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

For a simple tool with one optional parameter, the description covers output, usage scenarios, data origin, caching, and privacy. It is complete enough for an agent to decide when and how to use 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 coverage is 100% with enum descriptions. The description adds contextual guidance on window choice (shorter for hot, longer for steady-state), which helps agents select the right parameter value. While not extensive, it adds meaningful decision support.

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 returns top tools, top packs, and total call volume over a selected window. It uses a specific verb-retrieve pattern and distinguishes itself from sibling tools by focusing on trending data from Pipeworx.

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 explicit use cases (discovering hot data sources, confirming canonical choices, seeing alignment) and hints at window selection trade-offs. It does not explicitly mention when not to use the tool or compare with siblings, but the context is sufficient for most agents.

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

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

Adds extensive behavioral context beyond annotations: explains the algorithms (monotonicity, partition checks, semantic anchor, partition filter, fill check). Discloses that fill check may yield realizable_edge_pp ≤ 0 meaning the arbitrage is not tradable. No contradiction with annotations (readOnlyHint, openWorldHint, 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?

The description is dense and informative, with no wasted sentences. However, it is quite long and could benefit from more structured layout (e.g., bullet points for modes). Front-loaded with main purpose.

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

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

Despite lack of output schema, the description details the response structure (opportunities[], partition_check fields, fill check fields). Covers edge cases (Jaccard similarity, placeholder filter, book depth). Also references sibling tool for further use. Very complete for a moderately 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 greatly expands on parameter semantics: for event it explains slug format and URL acceptance; for topic it explains cross-event scanning and gives example seeds. Adds meaning 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?

The description clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It differentiates three modes: no-args trending scan, event-specific, and cross-event topic scan. This distinguishes it from siblings like polymarket_edges and polymarket_fill_risk.

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 on when to use each mode: no args for trending scan, event for a specific market slug, topic for cross-event scanning. It explains the advantage of cross-event mode and recommends using polymarket_fill_risk for custom sizing, providing an 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 declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds rich behavioral detail: caching (1h at KV level), response structure with diagnostics, model family explanations, edge calculation with slippage, and empty segment reasons. No contradiction.

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

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

Description is thorough yet efficiently structured. Each section (purpose, model families, opportunity fields, knobs, response structure) is front-loaded with key info. Every sentence adds value for a complex tool with 9 parameters and intricate output.

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

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

Despite no output schema, the description fully explains return structure (by_segment, fed_candidates, diagnostics) and per-opportunity fields (edge_pp_net, kelly_fraction, liquidity, spread, volume, 24h move warning). Covers filter behavior and empty segment diagnostics, making it complete for agent 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?

All 9 parameters have full schema coverage (100%). The description goes deeper, explaining parameter interactions (e.g., min_kelly skips small opportunities, min_partition_leg_kelly applies to per-leg Kelly inside partitions), use cases, and default behaviors, adding significant 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?

Description clearly states the tool scans top Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It distinguishes itself from sibling tools like polymarket_arbitrage, polymarket_edge_tracker, etc. with a specific use case: 'what should I bet on today'.

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 the tool is built for agents to discover opportunities without paging hundreds of markets. Provides detailed knob settings (min_liquidity, max_spread_pp) and explains when to use filters, giving clear guidance on 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?

The description adds significant behavioral context beyond annotations: it explains the source (daily snapshots), return structure (tracked, expired, snapshot_dates), computation details (decay from daily closes, not intraday), and limitations (60-day TTL, snapshot gaps). Annotations already confirm read-only, idempotent, non-destructive, and the description aligns with 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 detailed and front-loaded with the core purpose. While every sentence adds value, it is relatively long. The structure is clear: purpose, arguments, response format, limitations. Minor redundancy with schema could be tightened.

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 fully covers the return values (tracked, expired, snapshot_dates), explains how each is computed, and notes limitations. With no output schema, the description bears the full burden and succeeds. All aspects of using the tool are addressed.

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

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

Both parameters are documented in the schema with defaults and ranges. The description repeats this information but does not add substantial new semantics. Given 100% schema coverage, baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: analyzing edge persistence and decay from daily snapshots. It specifies the core question answered ('how long has this edge existed and is it shrinking?') and distinguishes itself from sibling tools like polymarket_edges by focusing on persistence telemetry.

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 on when to use the tool (e.g., distinguishing between fresh and old edges) and explains the response structure. However, it does not explicitly exclude alternatives or provide conditions when not to use it.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint false. The description adds behavioral nuances: it walks the order book ladder, returns a verdict (clean|degraded|cannot_fill), and warns about forced directional risk. This enriches the annotation baseline 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 well-structured with bullet points, front-loaded with the purpose, and every sentence adds value. It uses formatting (capitalization, line breaks) to improve readability without being verbose.

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

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

Despite no output schema, the description thoroughly documents return fields for both modes (e.g., top_of_book, vwap_fill_price, capture_ratio, thin_legs). It covers edge cases like partial fills and forced directional risk, making it complete for an agent to invoke correctly.

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

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

Schema coverage is 100%, so baseline is 3. However, the description significantly enhances parameter meaning: explains how size_usd is interpreted differently for buys vs sells and for single-market vs basket, details the side auto-detection for basket mode, and clarifies defaults. This adds substantial 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 the tool's purpose: 'Realizable-vs-theoretical edge check against live CLOB order-book depth.' It distinguishes between single-market and basket modes, specifying what each does and the returned fields. This goes well beyond a tautology and effectively differentiates from sibling 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?

Explicit usage guidance is provided: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains the risks of partial fills converting an arb into an unhedged directional position, giving clear context for when to use this tool versus 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 indicate readOnlyHint=true and description confirms no mutations. Safety fields (compatibility_warning, temporal_alignment, skipped metrics) are fully explained, disclosing edge cases and limitations.

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 front-loaded with purpose, uses clear sections (TWO MODES, RESPONSE, SAFETY FIELDS), and every sentence adds necessary information without redundancy.

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

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

With no output schema, the description adequately explains return values (leg-by-leg prices, top_spreads_pp, safety fields) and covers all scenarios, leaving no gaps for an agent to misuse the tool.

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

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

Schema coverage is 100%, and the description enriches each parameter with details: topic lists all 10 shortcuts, kalshi_event_ticker and polymarket_event_slug are described as overrides with example formats.

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 tool computes cross-venue spread between Kalshi and Polymarket for the same question, differentiating it from sibling tools like polymarket_arbitrage or polymarket_edges. It clearly identifies the resource and action.

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

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

Two distinct modes (topic shortcuts vs explicit tickers) are described with examples. The description warns that most pre-mapped topics are not tradeable and explains when compatibility_warnings arise, guiding appropriate use.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, indicating safe retrieval. The description adds behavioral details: listing all keys when argument omitted, scoping to a user identifier, and pairing with sibling tools. No contradictions.

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

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

Two sentences with no wasted words. Every sentence adds value: first defines action, second explains usage with examples and pairing. Well-structured and front-loaded.

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

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

Given the low complexity (one optional parameter, no output schema), the description fully covers purpose, usage, scoping, and relationships with siblings. No gaps remain.

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

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

The schema has 100% coverage with a description for the 'key' parameter. The description restates the schema's behavior (omit to list all) but does not add new semantic meaning. Baseline 3 is appropriate.

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

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

The description uses a specific verb 'retrieve' and identifies the resource as 'a value previously saved via remember'. It clearly distinguishes itself from sibling tools ('remember' and 'forget') and provides concrete examples of use cases (ticker, address, research notes).

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

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

The description explains when to use the tool ('look up context the agent stored earlier', 'without re-deriving it from scratch') and mentions related tools ('Pair with remember to save, forget to delete'). It does not explicitly state when not to use it, but the guidance is clear and practical.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds meaningful behavioral context: how mark_read=true affects subsequent calls, that polling works fine, and the existence of an alternative GET endpoint. It does not contradict annotations and enhances understanding beyond what annotations convey.

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

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

The description is a single, well-structured paragraph that front-loads the main action. Every sentence adds value without redundancy. It is appropriately sized for the tool's complexity.

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

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

Given there is no output schema, the description adequately explains return values (source, citation_uri, raw payload). It also covers the alternative endpoint and polling behavior. For a read-only tool with 5 optional parameters, this is contextually complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds value by explaining the effect of mark_read on the feed state, specifying that 'since' expects an ISO timestamp, and clarifying the default limit. This goes beyond the schema descriptions, earning 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 pulls fired events from the subscription feed, returns recent alerts with specific fields (source, citation_uri, raw payload), and distinguishes from the alternative GET endpoint for scripts/dashboards. The verb 'pull' combined with the resource 'fired events from your subscription feed' provides a precise purpose.

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

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

The description explains when to use polling, how to filter by type and timestamp, and the mark_read behavior. It mentions the alternative endpoint for scripts/dashboards, which provides context for when not to use this tool. However, it does not explicitly compare to sibling tools like list_subscriptions or subscribe, so a minor gap exists for exclusive usage guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive. The description adds valuable behavioral details: fans out to multiple sources, fallback logic (GDELT preferred, GNews when rate-limited/5xx), USPTO soft-fails until reactivated, and return structure with 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?

The description is slightly long but front-loaded with example queries. Every sentence provides useful information, but could be trimmed slightly.

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

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

Despite no output schema, the description explains the return shape (changes grouped by source, total_changes count, citation URIs). Together with good annotations, it is complete for a complex tool with multiple sources and fallbacks.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaning beyond schema: explains since accepts ISO date or relative shorthand with examples, clarifies type only supports 'company', and value can be ticker or CIK. This adds value.

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

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

The description starts with example queries that clearly illustrate the tool's purpose. It states it provides a change feed for a company from SEC EDGAR, GDELT/GNews, and USPTO in one parallel call. It also distinguishes from sibling entity_profile, which is for static profiles.

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

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

The description explicitly tells when to use this tool vs entity_profile, and provides guidance on the since parameter format. However, it does not address when to use other sibling tools.

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

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

Annotations indicate idempotentHint=true and destructiveHint=false, and the description adds persistence details (authenticated users get persistent memory; anonymous sessions 24 hours). This goes beyond annotations, though it could explicitly mention idempotency.

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 serving a distinct purpose: stating function, advising usage, and detailing storage behavior. No wasted words; information is efficiently front-loaded.

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

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

Given the simple write operation with no output schema, the description adequately covers purpose, usage timing, persistence behavior, and pairing with sibling tools. No gaps identified.

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

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

Schema coverage is 100% with parameter descriptions already providing format hints. The description adds context of key-value pairing scoped by identifier but doesn't significantly enhance 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 the tool stores data for reuse across conversations/sessions, with specific examples of what to store (resolved ticker, address, preference, research subject). It explicitly mentions sibling tools 'recall' and 'forget', making its purpose distinct.

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 guidance on when to use the tool ('when you discover something worth carrying forward') and references sibling tools for retrieval and deletion. It lacks explicit when-not-to-use cases but effectively implies 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?

The annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context beyond these by specifying data sources (SEC EDGAR for companies, RxNorm for drugs), exact return fields (ticker, CIK, company_name; RxCUI, ingredient, brand), and the citation URIs generated. It also notes the internal cascading lookup behavior. This gives the agent a richer mental model of what happens behind the scenes.

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 directive up front, query examples, and a SUPPORTED TYPES breakdown. It is somewhat long but every sentence contributes functional information. The examples could arguably be shorter, but they help recognize user intents. Overall, it is efficient and front-loaded.

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

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

Considering the tool has two entity types, no output schema, and rich annotations, the description covers the essential return values and sources for each type. It also notes the auto-disambiguation and cascade behavior. It could mention error cases or what happens with invalid input, but for a read-only lookup tool this is a solid, near-complete description.

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

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

The schema already provides 100% coverage for both parameters: 'type' has an enum, and 'value' includes format examples for both entity types. The description reinforces the accepted input forms (ticker/CIK/name, brand/generic) and mentions auto-disambiguation, but this is largely redundant with the schema. Per the rubric, baseline is 3 because schema coverage is high.

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

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

The description clearly states the tool resolves user-spoken names to canonical/official identifiers needed by other tools. It provides concrete query examples (ticker, CIK, RxCUI) and distinguishes this from related tasks like entity profiles or search. The verb 'resolve' plus the resource (identifiers) makes 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 says 'Use FIRST whenever you have a name but need an ID', which is a strong usage directive. It also explains that it replaces 2-3 manual lookups and notes that other tools require these IDs as input. However, it does not explicitly name alternative tools or state when not to use it (e.g., when you already have the ID).

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, open-world, non-destructive. Description adds that it probes each entity internally using ai_visibility_check and returns a ranked list with score, confidence, signal density. No contradiction.

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

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

Three concise sentences front-loaded with purpose and action. Every sentence adds distinct value with no redundancy.

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

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

Given no output schema, the description adequately specifies return type (ranked list with score, confidence, signal density per entity). Combined with annotations, the tool is fully described.

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

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

Schema has 100% coverage with descriptions for all 4 parameters. Description adds value by specifying that the first entity is treated as the 'subject' with narrative, and that models default to workers-ai if omitted.

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

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

The description clearly states it compares AI visibility across multiple entities side-by-side, using ai_visibility_check internally, ranks by score, and surfaces most/least recognized. This distinguishes it from sibling ai_visibility_check which handles a single entity.

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

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

Provides explicit use case ('competitive AI-marketing audits') with an example question. Does not explicitly state when not to use (e.g., for single entity use ai_visibility_check), 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, idempotentHint, destructiveHint. The description adds critical behavioral context: bundlephobia's first measurement can take 5-30s, partial failures degrade gracefully, and sources_failed field is included. 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 a single dense paragraph, but every sentence adds value. It could be slightly more structured (e.g., bullet points for return fields), but it is not 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?

Despite no output schema, the description thoroughly lists return fields: summary block, per-advisory detail, links, and alternative versions. It also addresses edge cases (partial failures, timing) and scope limitations. Complete for the tool's complexity.

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

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

Schema coverage is 100% with both parameters documented. The description clarifies that scoped packages are accepted for 'package' and that 'version' defaults to latest when omitted. This adds minor 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 it is a composite check for npm packages covering license, advisories, version history, and bundle size. It distinguishes itself from siblings by specifying 'NPM ecosystem only' and noting that other ecosystems are handled by a different tool.

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

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

Explicitly says 'Use whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'. Also specifies limitations: only npm in v1, with clear alternatives for other package managers.

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. Description adds embedding model (BGE-base-en), similarity metric (cosine), windowing (500-char overlapping), and character cap (200K chars with truncation flag). 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?

Front-loaded with purpose and usage. Technical details are included but not excessive. Could be slightly more concise 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 description mentions character offsets and similarity scores but does not detail exact return structure. Includes cap and truncation. Acceptable but could be more complete.

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

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

Schema coverage is 100%. The description doesn't add extra meaning beyond the schema descriptions for text, query, and limit. 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 semantic search inside a fetched record with examples like SEC 10-K body. It distinguishes from siblings by mentioning pairing with ask_pipeworx_grounded and focusing on internal search.

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

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

Explicitly states when to use: when the record is too big for the prompt. Also mentions pairing with ask_pipeworx_grounded. No explicit exclusions but context is clear.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint false. The description adds valuable behavioral details: what is returned (shaped notice including title, description, CPV classification, etc.) and specifics for award publications. 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 a single, well-structured sentence that efficiently conveys purpose, input requirements, and output details without wasted words. It is front-loaded with the core action.

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

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

Given the lack of an output schema, the description thoroughly explains the return fields, including specific details for award publications. Combined with sibling tool references, it provides complete context for an agent to use the tool correctly.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description adds context that the IDs are UUIDs from sibling tools, which aids understanding beyond the schema. Baseline 3, increased due to added value.

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

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

The description clearly states the tool fetches the full detail of one Swiss public procurement publication from simap.ch by project_id and publication_id. It distinguishes itself from sibling tools like simap_search and simap_recent by focusing on a single publication's details.

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

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

The description explains that the IDs are returned by simap_search or simap_recent, indicating when to use this tool (after search/recent). It does not explicitly state when not to use, but the context is clear and provides actionable guidance.

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

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

Annotations already indicate readOnlyHint, idempotentHint, etc. The description adds behavioral context: results are newest first, 20 per page with cursor pagination, and it covers federal, cantonal, and municipal notices. 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 that immediately state the purpose and key features. No unnecessary words; 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 the complexity of 5 optional parameters and no output schema, the description adequately covers what results to expect (newest first, 20 per page, cursor pagination) and the data source (simap.ch). It also mentions it is a wrapper over simap_search for context.

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

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

Schema coverage is 100% with descriptions for all 5 parameters. The description adds the default for days_back (7) and mentions that cantons and pub_types are optional filters with comma-separated values, but this adds only marginal value over the schema. Baseline 3 is appropriate.

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

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

The description clearly states it lists the most recent Swiss public procurement notices from simap.ch, using a specific verb ('List') and resource ('Swiss public procurement notices'). It distinguishes itself from the sibling tool simap_search by calling itself a 'convenience wrapper' and specifying its focus on recent notices with a days_back parameter.

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

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

The description explains when to use this tool: for monitoring recent tenders with days_back, optionally filtered by canton or publication type. It also positions itself as a convenience wrapper over simap_search, implying that for more advanced search, one should use simap_search. However, it does not explicitly state when not to use it or list alternatives beyond simap_search.

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 read-only, idempotent, non-destructive behavior. The description adds pagination details (20 per page, cursor, newest-first order), return format elements (title, buyer, canton, date, URL), and price currency (CHF). 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, front-loaded with purpose and usage guidance, and efficiently lists filter capabilities. Could be slightly more structured with bullet points, but overall effective.

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

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

Given the complexity (10 parameters, none required, full schema coverage, no output schema), the description provides complete context: purpose, filter types, pagination, ordering, default behavior (30 days), and currency. No gaps identified.

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

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

Schema coverage is 100% with well-described parameters. The description provides a summary of filters but does not add significant meaning beyond what the schema already offers. Baseline of 3 is appropriate.

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

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

The description clearly states it searches Swiss public procurement notices on simap.ch with specific verb and resource. However, it does not differentiate from sibling tools simap_project or simap_recent, leaving ambiguity for when to choose this tool over them.

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

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

Explicitly recommends using this tool over web search for Swiss government tenders, explaining the reason (Switzerland non-EU). It also provides filter usage examples, but lacks when-not-to-use or explicit alternatives among siblings.

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

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

Beyond annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description details delivery channels, sms cap, webhook auto-disable, and the returned subscription id. It does not clarify idempotency behavior for duplicate subscriptions, but overall provides good behavioral context.

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

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

The description is moderately long but well-structured with bullet-like lists and front-loaded purpose. It could be slightly more concise, but effectively conveys necessary details without excessive verbosity.

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 types, delivery channels, OAuth requirement), the description covers nearly all essential aspects. Minor gaps include rate limits on subscription creation and idempotency behavior. No output schema, but the return value is mentioned.

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, but the description adds rich examples and details for each type (e.g., sec_8k items, polymarket_edge topic) and delivery options (webhook signing, sms verification), significantly enhancing param 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 explicitly states 'Create a proactive monitoring subscription to a live-data event stream' and specifies it returns the new subscription id. It clearly distinguishes from sibling tools like list_subscriptions 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 provides clear context for when to use the tool, including the requirement for a Pipeworx OAuth account and that the feed is always accessible via recent_alerts. However, it could more explicitly state when not to use subscribe (e.g., if only pulling existing alerts).

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. Description adds value by explaining it returns example questions and tool argument shapes, with no contradiction. Could mention that it does not modify state, but annotations already cover that.

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

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

Description is thorough and front-loaded with common questions. Though slightly long, every sentence adds value and it remains clear and well-structured.

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

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

For a simple tool with one optional parameter and no output schema, the description fully covers what the tool does, when to use it, and what it returns. No gaps remain.

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 significant meaning: lists possible topic values (finance, pharma, etc.) and explains the effect of omitting the parameter. Exceeds baseline expectations.

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: an onboarding entry point for agents to discover what Pipeworx can do, returning category-bucketed example questions. It distinguishes from sibling tools by specifying when to use it first.

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 instructs to use this tool FIRST when unsure about Pipeworx's capabilities. Provides guidance on calling with no arguments for full spread or with a specific topic, and lists example topics.

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

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

Description adds critical context beyond annotations: row is deactivated not deleted, and historical events remain accessible via recent_alerts. This aligns with destructiveHint=false and idempotentHint=true.

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

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

Two efficient sentences: first states core purpose, second adds behavioral nuance. No redundant or extraneous content.

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

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

For a simple tool with one parameter and no output schema, the description fully covers purpose, ownership, and effect. No gaps.

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

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

Schema coverage is 100% with a clear description of the 'id' parameter. Description does not add further detail beyond what schema provides, so baseline 3.

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

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

Clearly states the verb 'Cancel' and resource 'subscription by id'. Distinguishes 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 mentions ownership enforcement — agents know to use only for own subscriptions. No explicit when-not or alternatives, but sibling name 'subscribe' provides contrast.

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, open-world, idempotent, non-destructive. Description adds detailed behavioral context: two verification paths (SEC EDGAR vs grounded pipeline), tolerance handling, output format (verdict, citation, reasoning). No contradictions.

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

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

Description is thorough yet concise, starting with synonyms and use cases, explaining the two pipelines, then output format. Every sentence adds value, no repetition.

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 of claim verification, the description covers purpose, usage, behavior, parameters, and return values. No output schema exists, but description explains verdict types, evidence, and reasoning. Complete for an agent to use correctly.

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

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

Schema coverage is 100% with descriptions. Description adds examples for claim and provides usage guidance for tolerance_pct (overriding defaults, recommended values for hallucination detection), going 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 does natural-language claim verification against authoritative sources with synonyms and examples. It differentiates from siblings by mentioning it replaces 4-6 sequential calls, though not naming specific alternatives.

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 whenever the agent needs to check whether something a user said is factually correct.' It distinguishes between financial and other claims with two pipelines, but does not explicitly list when not to use or name alternatives.

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