Airnow

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: scoring system, per-model response structure, and cost implications for Anthropic calls. 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?

Six sentences, each serving a purpose. Front-loaded with main action and output, then details on models, return format, and use cases. No redundant words.

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

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

With 4 parameters (1 required) and no output schema, the description explains return format (per-model fields + combined view) and covers key use cases. Provides enough context for correct selection and invocation.

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

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

Schema coverage is 100% with descriptions for all parameters. The description adds meaning about default model, which models require _apiKey, and that Anthropic calls are paid separately, enhancing understanding.

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

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

The description clearly states the verb 'probe', resource 'LLMs', and outputs 'visibility score (0-100) per model'. It distinguishes itself from siblings by focusing on brand visibility probing, unlike ask_pipeworx or deep_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?

The description lists use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring'. It explains default model and when to provide _apiKey but does not explicitly state when not to use or compare to 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context beyond this: it returns structured answers with stable pipeworx:// citation URIs, works on every tier, and is a single fast call. It does not contradict annotations, though it omits potential failure modes or rate limits.

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

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

The description is long but every sentence earns its place. It front-loads the key directive 'PREFER OVER WEB SEARCH', then provides structured details with examples and escalation paths. It is well-organized and avoids fluff, making it appropriately sized for a default entry-point 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 broad scope (routing to 5,358 tools), the description is remarkably complete. It covers what types of questions to use it for, what it returns (structured answers with citations), when to escalate to alternatives, and provides concrete examples. No output schema exists, but the description adequately explains return behavior.

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

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

Schema coverage is 100%: the 'question' property is fully described, and all aliases (q, text, input, query, prompt) are explicitly documented. The description itself does not add parameter-level details, but the schema already carries the full burden, so a 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 what the tool does: 'Routes the question to the right one of 5,358 tools across 1395 verified sources, fills arguments, returns the structured answer with stable pipeworx:// citation URIs.' It also explicitly distinguishes itself from siblings like ask_pipeworx_grounded and deep_research, making its purpose unambiguous.

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

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

The description provides explicit when-to-use guidance: 'PREFER OVER WEB SEARCH', 'START HERE for most questions', and 'Step up only when needed' with named alternatives (ask_pipeworx_grounded for hallucination-resistant answers, deep_research for broad/multi-part questions). It also lists trigger phrases like 'what is', 'look up', and gives concrete examples.

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, open-world, idempotent, and non-destructive. The description adds valuable behavioral context: it is a live experimental edge with candidate routing improvements toggled on/off, currently no candidate active, fully functional with no fallback, and identical response shape to ask_pipeworx. This exceeds annotation coverage.

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

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

Three sentences with no fluff, each earning its place. The description is front-loaded with the core identity ('Beta version of ask_pipeworx'), then covers current state and usage. The specific date adds useful context 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 is remarkably complete: it states identical behavior to ask_pipeworx, same arguments and response shape, the experimental nature, current inactive candidate, and that it is a full working router. This covers the essential context for an agent without needing further details.

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

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

Schema coverage is 100% with descriptions for all alias parameters, including a clear statement that they are aliases for 'question'. The tool description merely says 'same arguments,' adding nothing beyond the schema, so the baseline of 3 is appropriate.

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

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

The description clearly identifies the tool as the beta version of ask_pipeworx, an identical universal router with the same 5,358 tools and arguments, differing only in possibly improved routing. It explicitly distinguishes from the stable ask_pipeworx and other siblings by its experimental nature.

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 gives explicit when-to-use guidance: 'Use it exactly like ask_pipeworx when you want the newest routing.' It also explains the current state (no active candidate, matches stable exactly) and notes that results are compared against the stable router, clarifying its purpose for experimental evaluation.

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, openWorld, idempotent, and non-destructive annotations, the description discloses the refusal behavior with specific reasons (not_in_source, no_tool_match, etc.), the grounding mechanism (uses ONLY what the tool result contains), and the output structure including evidence and confidence. It also notes the additional LLM call overhead, providing valuable 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?

Despite being relatively long, every sentence carries unique information: the mode, routing, extraction method, output/refusal shapes, use cases, and cost comparison. The structure uses dashes and parenthetical lists effectively, with no redundant phrases, making it appropriately dense 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?

With no output schema, the description fully specifies the success return object and the refusal variants. It also covers the routing context, source count, and the performance tradeoff, providing all necessary information for an agent to decide when to invoke this tool 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?

The input schema provides 100% coverage of all six parameters, all documented as aliases for the 'question' parameter with descriptions. The description adds no parameter-specific semantics beyond what the schema already states, so it meets the baseline for high schema coverage without further compensation needed.

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

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

The description clearly identifies the tool as a hallucination-resistant answer mode for high-stakes reads, with a specific verb 'EXTRACTS' and resource 'tool result'. It distinguishes itself from the sibling 'ask_pipeworx' by emphasizing grounded extraction and explicit refusal reasons, making its purpose unambiguous.

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

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

It explicitly states when to use the tool: whenever an answer will be quoted, cited, or acted on, and when facts must not be invented. It also provides an alternative: 'prefer ask_pipeworx for casual lookups' and quantifies the cost tradeoff (one extra LLM call), offering clear decision 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, openWorldHint, idempotentHint, and non-destructive behavior. The description significantly adds value by detailing the resolution process, classification, parallel fan-out, response shapes, safety blocks, cancellation rules, and handling of illiquid markets, with no contradictions to annotations.

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

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

The description is verbose with multiple sections (RESPONSE SHAPES, RESOLVER CONTRACT, etc.). While structured and informative, it could be more concise without losing critical details. The length may still be acceptable for a complex tool, but it does not achieve maximum conciseness.

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

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

Given the tool's complexity (3 parameters, no output schema), the description covers all necessary aspects: usage, behavior, response structure, edge cases, safety, resolution risks, and field explanations. It is highly complete and leaves little ambiguity for an AI agent.

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

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

Schema coverage is 100% with clear descriptions for all three parameters. The description enhances understanding by explaining the market parameter accepts slug, URL, or question text; depth affects evidence count; and include_raw controls payload size. This goes beyond the schema, justifying a score above baseline 3.

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

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

The description explicitly states the tool researches a Polymarket bet by pulling Pipeworx data in one call, with a specific verb, resource, and scope. It distinguishes from sibling tools like polymarket_arbitrage and polymarket_edges by offering a comprehensive one-call research, making its purpose unique and clear.

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

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

The description provides explicit usage scenarios such as 'should I bet on X', 'what does the data say about Y', and 'is there edge in Z'. It also discusses blocking conditions (low-confidence matches, closed markets) but does not directly contrast with sibling tools, missing an opportunity to clarify when to use alternatives.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds valuable behavioral context: data sources (10-K, FAERS), handling of fiscal years, 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 packed with useful information but is somewhat long. However, every sentence adds value, and the structure with examples and specifics is effective. A bit verbose but not wasteful.

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 (two entity types, multiple data sources, sorting, citations), the description covers all necessary aspects. Explains return format despite no output schema. 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%. The description adds meaning beyond the schema by explaining that 'values' expects tickers/CIKs for company and drug names for drug, and reinforces min/max constraints. Provides clarity on usage.

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: side-by-side comparison of 2-5 companies or drugs in one parallel call. It lists common query phrasings and distinguishes from sequential single-pack lookups, making the purpose unambiguous.

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

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

Explicitly states 'ALWAYS PREFER over sequential single-pack lookups' and describes when to use company vs drug type. Lacks explicit exclusion for more than 5 entities, but otherwise provides strong 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 read-only, idempotent, and non-destructive behavior. The description adds 'latest observed' and 'nearest station' but does not disclose edge cases like missing stations or single-result limitation. With annotations present, the description provides adequate but not extra 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?

A single clear sentence with no redundancy. Every word adds value and the purpose is immediately understood.

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

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

Given the tool's simplicity, the presence of annotations, a complete input schema, and an output schema, the description is sufficiently complete. It succinctly describes the core function without needing further detail.

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

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

Schema description coverage is 100%, so all parameters are documented in the schema. The description does not add additional semantics beyond what the schema already provides. Baseline 3 is appropriate.

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

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

Description clearly states the tool returns the latest AQI for the nearest AirNow station given lat/lon coordinates. This differentiates it from the sibling tool 'current_by_zip' which uses a ZIP code.

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

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

The description implies usage when latitude and longitude are available, but does not explicitly state when to use this tool over alternatives like 'current_by_zip' or mention any exclusions. Guidance is minimal but not misleading.

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 openWorldHint. The description adds behavioral specifics: returns one record per pollutant, uses nearest site, includes category and timestamp. This context goes beyond 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 convey the core purpose, return structure, and typical behavior. No extraneous content; front-loaded with the primary action. Highly efficient.

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

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

Given the output schema exists (context signal) and annotations provide safety profile, the description is complete for a simple read tool. It explains what data is returned and the geographical resolution (nearest site). No obvious 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?

The input schema covers 100% of parameters with descriptions for zip_code and distance_miles. The description does not add new parameter information, so it relies on 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 the tool returns the latest observed AQI for a US ZIP code, specifying it returns one record per pollutant (typically O3 and PM2.5) with AQI value, category, area, and timestamp. This distinguishes it from sibling tools like current_by_location (which uses lat/lng) and forecast_by_zip (forecast).

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 implicitly defines usage: querying current AQI by ZIP. However, it does not explicitly state when to use this tool versus alternatives like current_by_location or forecast_by_zip, nor does it mention exclusions (e.g., non-US ZIPs). Sibling tools are listed in context but not referenced in the description.

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

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

The description discloses extensive behavioral traits beyond annotations: account/paywall requirements, parallel decomposition across 5,358 tools, return packet schema (verbatim evidence + confidence + source + fetched_at + citation), explicit gaps[] and contradictions[], second-hop iteration behavior, semantic excerpting, and expected latency ('15-60s... up to ~90s'). The readOnlyHint etc. are not contradicted.

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, front-loaded with critical access caveats, and every major behavior earns its place. Some redundancy with schema descriptions exists, but the richness of the tool warrants the length. It reads as a comprehensive guide without wasted filler.

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

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

For a complex, multi-behavior research tool with no output schema, the description is exceptionally complete: it covers prerequisites, input expectations, process, output format, limitations, latency, and edge cases (e.g., empty gaps for non-catalog topics). It leaves no significant operational question unanswered.

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 already covers both parameters at 100% with detailed explanations (e.g., depth enum behaviors). The description restates some of this (e.g., 'thorough' paid, contradiction scan) but adds no new syntactic or format guidance beyond what the schema provides. Thus 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 performs 'grounded multi-source research' across structured data sources in one call, with specific scope ('SEC filings, FRED/BLS economics...') and explicitly contrasts with siblings: 'this is NOT open-web search' and recommends ask_pipeworx for single lookups or breaking news. The verb 'research' plus resource and scope differentiate it 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?

Provides explicit when-to-use and when-not-to-use guidance: 'Best for broad/multi-part questions over structured data', 'For a single lookup use ask_pipeworx', 'For BREAKING... prefer ask_pipeworx'. It names alternatives and even notes account requirements, including 'If you are not signed in, use ask_pipeworx instead'.

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

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

Discloses that results include schemas and are ready to call directly; annotations already indicate read-only and idempotent behavior. No contradictions, but could add more about limits or side effects.

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

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

Description is structured with front-loaded purpose, each sentence adds value, though slightly long for a search-like 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 6 parameters and no output schema, description adequately covers return format and usage context, with examples and note on direct callability.

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 aliases and examples already documented; description adds usage examples but does not provide new meaning beyond what schema offers.

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 'Find tools by describing the data or task' and lists specific domains, differentiating from siblings by advising to call this FIRST when exploring the option set.

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

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

Explicitly tells when to use ('Use when you need to browse...') and advises 'Call this FIRST', but does not explicitly state when not to use or name alternative tools, though context is sufficient.

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

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

Annotations already indicate readOnly, openWorld, idempotent, non-destructive. Description adds significant behavioral context: fans out across multiple sources, returns specific fields (CIK, filings, fundamentals, patents, news, LEI), mentions soft-fail for patents, and notes one parallel call. 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 a single dense paragraph but is front-loaded with example queries. Every sentence adds value, but it could be slightly more structured (e.g., bullet points for return fields) without losing information. Still, it is efficient and not overly verbose.

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

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

Given no output schema, the description comprehensively lists return fields (CIK, company_name, recent_filings, fundamentals, patents, news, LEI) with sufficient detail (e.g., URIs, sort order, potential soft-fail). It also explains input constraints and usage context. Minor gaps like error handling are acceptable for a profile tool.

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

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

Schema coverage is 100% with both parameters described. Description adds value by reinforcing that 'value' can be ticker or zero-padded CIK, names are not supported, and providing format details (e.g., '0000320193'). It also clarifies the 'type' enum is currently limited to 'company'.

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 starts with diverse example queries, then states the tool's purpose clearly: 'full cross-source profile of a US public company in ONE parallel call.' It distinguishes itself from sibling tools like resolve_entity and compare_entities by highlighting its holistic, multi-source approach.

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: 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' Also explicitly states when not to use: 'Names not supported (use resolve_entity first if you only have a name).' Provides clear context and 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 comprehensive behavioral hints (readOnly, openWorld, idempotent, non-destructive). The description adds no additional behavioral context beyond what is in the annotations. This is adequate but not extra.

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

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

The description is two sentences, front-loaded with the primary action, and contains no unnecessary words. It efficiently conveys the tool's purpose and a typical use case.

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

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

Given that an output schema exists, the description does not need to explain return values. It covers the main purpose and date default but does not mention the distance_miles parameter. Still, the tool is relatively simple and the schema handles remaining details.

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

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

Schema description coverage is 100%, so the input schema already documents all parameters. The description only restates the date default, adding no new semantic meaning beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly defines the tool as providing an AQI forecast for a US ZIP code on a given date, with a default to today. It uses a specific verb (forecast) and resource (AQI), and distinguishes from sibling tools like current_by_zip by focusing on future predictions.

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 a use case ('is tomorrow ok for outdoor activity'), implying when this forecast tool is appropriate. While it does not explicitly contrast with current conditions tools, the context is clear enough for the agent to differentiate from 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?

Annotations already indicate destructiveHint=true, and the description confirms the delete behavior. It adds context about clearing stale/sensitive data, but the core transparency is already covered by 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 with no wasted words. Front-loaded with the action, followed by usage guidance. Every sentence adds value.

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

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

For a simple delete tool with one parameter and no output schema, the description fully covers purpose, usage, and behavioral context. 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?

Schema coverage is 100% with a clear parameter description. The description does not add additional meaning beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states 'Delete a previously stored memory by key', specifying the verb, resource, and means. It distinguishes from siblings by mentioning 'remember' and 'recall'.

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

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

Explicitly provides when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Also suggests pairing with 'remember' and 'recall', aiding tool selection.

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

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

Annotations already indicate readOnlyHint, idempotentHint, and non-destructive behavior. The description adds the process (fetches page, extracts title/description/links) and output format (single text blob for site-root/llms.txt), 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?

The description is two sentences plus a usage note, with no redundant information. It is front-loaded with the core purpose and succinctly covers all essential aspects.

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

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

The tool is simple with two parameters and no output schema. The description explains the output format and use cases fully. Given the annotations and schema richness, no further details are needed.

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

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

Schema coverage is 100% with clear descriptions for both parameters (url and max_links). The description does not add substantial new meaning beyond what the schema provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the tool generates a production-ready llms.txt file for any URL, specifying the verb (generate), resource (llms.txt), and purpose (AI crawler indexing). It distinguishes from sibling tools like ai_visibility_check and scan_competitor_ai_presence by focusing on output generation rather than analysis.

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

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

The description provides explicit use cases: getting a client's site indexed, drafting for own project, or auditing competitor visibility. It does not explicitly list when not to use or alternatives, but the context is clear enough for an agent to decide.

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

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

Annotations already declare readOnly and idempotent hints. The description adds value by listing return fields and implying default filtering of active subscriptions, but behavioral traits are well-covered by annotations.

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

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

The description is two sentences, front-loaded with purpose, and every sentence provides useful 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?

For a simple list tool with one optional parameter and sibling tools, the description is complete. It specifies return fields and usage context, sufficient 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%, so the parameter's description in the schema already explains include_inactive. The tool description mentions 'active' which hints at the default, but no additional meaning beyond schema.

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

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

The description clearly states the tool lists the caller's active subscriptions and specifies return fields, distinguishing 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?

The description provides guidance on when to use the tool: to review subscriptions before adding more or to find an id to cancel. It does not explicitly mention when not to use, but the context is clear.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds minimal behavioral context beyond the annotations, such as the bbox format and pollutant specification. It does not discuss pagination, rate limits, or data sparsity.

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

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

The description is two sentences long, front-loaded with the primary purpose, and contains no superfluous 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?

Given full schema coverage, annotations, and an output schema, the description covers the essential usage context. It could mention time granularity (hourly) or that results may include multiple sites, but the output schema likely clarifies this.

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 schema includes descriptions for all parameters. The description adds an example of pollutant codes but does not provide additional meaning beyond what the schema already conveys.

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

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

The description states it returns 'Historical AQI observations inside a bounding box for a date range,' which is a specific verb+resource combination. It clearly distinguishes itself from sibling tools that focus on current or forecast data, such as current_by_location or forecast_by_zip.

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

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

The description implies usage for historical AQI queries but does not explicitly state when to use this tool versus alternatives like current_by_location. There is no mention of caveats, limitations, or contraindications.

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

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

Discloses rate limit (5 per identifier per day), free usage, and that it doesn't count against tool-call quota. Annotations have no hints, so description fully handles transparency. 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?

Front-loaded with purpose, then use cases, then behavior. Every sentence adds value. No wasted words. Appropriate length (~5 sentences) for the 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 the tool's simplicity (3 params, no output schema), description covers all needed context: use cases, constraints (rate limit, free), what to include/avoid, and how feedback is used (roadmap impact). 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%, so baseline is 3. Description adds value by elaborating on enum meanings (e.g., 'bug = something broke or returned wrong data') and giving guidance on message length and specificity ('1-2 sentences typical, 2000 chars max'). Also explains context object purpose.

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's purpose: sending feedback to Pipeworx team about bugs, missing features, or praise. It uses a specific verb ('tell') and resource ('Pipeworx team'), and distinguishes from sibling tools (e.g., ask_pipeworx, discover_tools) which are for queries, not feedback.

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

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

Explicitly tells when to use: for bugs, feature requests, data gaps, praise. Also provides an exclusion: 'don't paste the end-user's prompt.' Clear context on when it's appropriate 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 declare readOnly, openWorld, idempotent, not destructive. Description adds: data source (CF analytics-engine), no PII, caching (5min-1h), and return format. This provides comprehensive 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?

Description is well-structured with bullet points. Every sentence is informative, no fluff. Appropriately sized for the tool's simplicity.

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

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

Given no output schema, the description explains return values (top tools, top packs, volume). Also covers data source, privacy, caching, and parameter details. Complete for a read-only trending tool.

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

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

Schema covers the single parameter (window) with enum and description. Description adds semantic guidance: shorter windows for hotness, longer for steady-state. This adds value beyond the schema.

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

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

The description clearly states the tool returns top tools, top packs, and call volume over a window. It distinguishes from sibling tools like ask_pipeworx or discover_tools by focusing on trending/aggregated signals.

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

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

Three explicit use cases are provided (discovering hot data sources, confirming canonical choice, aligning use case). No explicit when-not-to-use, but the context is clear enough to avoid misuse.

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

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

Beyond annotations (readOnly, openWorld, idempotent, non-destructive), description adds critical behavioral details: fill check with realizable_edge_pp ≤ 0 signal to not trade, semantic anchor for similarity, partition filter for placeholders, and response structure.

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

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

Very informative but somewhat dense; could be slightly more streamlined. However, it is front-loaded with the main purpose and modes, and each section 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?

With no output schema, the description fully explains return values (opportunities[], partition_check, fill check results) and trade implications. Covers edge cases like low similarity and placeholder filtering.

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

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

Schema coverage is 100% but description adds significant extra meaning: provides example values for event slugs and topics, explains URL acceptance, and describes mode-specific behavior for each 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 clearly states the tool finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes three modes (no-args trending scan, event mode, topic mode) and explains each, differentiating 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 guidance on when to use each mode: 'Call with NO args for a trending_scan', 'event (recommended for a specific market)', 'topic (for cross-event scanning)'. Also directs to polymarket_fill_risk for custom sizing.

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 significant behavioral context, including the three model segments, response structure with edge_pp_net and Kelly fractions, 24h-move warnings, caching behavior, and diagnostic counters, all beyond annotations.

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

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

The description is verbose, containing deep technical details about model formulas and internal logic. While well-structured with front-loaded purpose, it is not concise and could overwhelm an AI agent seeking quick understanding.

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

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

Given the complexity (9 parameters, no output schema, many siblings), the description is highly complete. It explains the response structure, caching, diagnostics, and tradeable-edge knobs in detail, compensating for the lack of an 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%, so baseline is 3. The description adds meaning by explaining tradeable-edge knobs (min_liquidity, max_spread_pp, min_partition_leg_kelly) and differentiating min_kelly vs min_partition_leg_kelly, which goes 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 scans Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It distinguishes itself from siblings by focusing on 'what should I bet on today' and avoiding paging through markets, which differentiates it from tools like polymarket_arbitrage.

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 indicates the tool is built for discovering opportunities without paging through markets, providing implicit usage context. However, it does not explicitly compare with sibling tools or state when not to use this tool, which limits the guidance.

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

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

The description adds significant detail beyond annotations: explains the trend and decay computation, the structure of response fields (tracked, expired, snapshot_dates), and limitations (60-day TTL, daily closes, not intraday). Annotations only indicate read-only, non-destructive, idempotent, open-world, so description enriches understanding.

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

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

The description is comprehensive yet each sentence adds value. It front-loads the core purpose, then details response structure, and ends with limitations. No filler or redundancy.

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

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

With no output schema, the description thoroughly explains the response: tracked[], expired[], snapshot_dates[], including field meanings and edge_pp_net interpretation. It also covers history bounds and data source. This makes the tool fully self-contained.

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 both parameters. The description repeats parameter info (lookback, clamp, default) but adds no new semantics beyond what schema provides. 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: providing edge persistence and decay telemetry from daily snapshots. It answers a specific question ('how long has this edge existed and is it shrinking?') and distinguishes itself from siblings like polymarket_edges by focusing on time-series, not just current edges.

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

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

The description implies usage for evaluating edge freshness versus age, contrasting 'fresh wide edge' with '3-week-old wide edge'. While it does not explicitly name alternative tools, the context from siblings and the tool's name makes the use case 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 read-only, open-world, idempotent, non-destructive. The description adds behavioral context: it simulates fills, walks ladder, returns verdict. It warns about thin books and partial fills, which goes beyond annotations. 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 detailed but well-organized with headings for each mode. It front-loads the purpose. While somewhat verbose, every sentence adds value and there's no filler.

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

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

Despite no output schema, the description fully explains return fields (top_of_book, VWAP, slippage, verdict, etc.) and covers edge cases like thin legs and forced directional risk. It addresses the dominant loss mode in arb bots.

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

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

Schema coverage is 100%, but the description adds value by explaining size_usd differently for single-market (spend/proceeds) vs basket (settlement notional), side defaults, and market vs event requirement. This goes beyond the schema's 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 it performs a realizable-vs-theoretical edge check against live order book depth, distinguishing single-market and basket modes. It uses specific verbs like 'check' and 'walks the ladder', and contrasts with sibling tools polymarket_arbitrage and polymarket_edges.

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

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

Explicitly instructs to use this tool before acting on arb signals or trades above $500. It explains why (partial fills convert arb to unhedged directional position) and distinguishes from alternative tools, leaving no ambiguity.

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 confirm read-only, idempotent, non-destructive behavior. The description adds extensive behavioral details: two modes, response structure (leg-by-leg prices, top_spreads_pp), safety fields (compatibility_warning, temporal_alignment, skipped counters), and conditions for meaningful spreads. 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 long but every sentence provides essential information. It is front-loaded with the core purpose and then details modes, response, and safety fields. A bullet list could improve readability, but it is not excessively 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?

Given the tool's complexity (multiple modes, safety checks, temporal alignment) and lack of output schema, the description is remarkably complete. It covers response fields, warning conditions, and explains why most shortcuts are not tradeable, leaving little ambiguity.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description adds value by explaining the modes and how topic maps to venues, and clarifies that explicit parameters override topic mappings. This goes beyond the schema, justifying 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 it is a cross-venue spread between Kalshi and Polymarket, with two modes (topic shortcuts and explicit tickers). This differentiates it from sibling tools like polymarket_arbitrage (intra-venue) and polymarket_edges.

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

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

The description explains when to use topic mode vs explicit mode, and warns that most topic shortcuts return compatibility warnings, setting realistic expectations. However, it does not explicitly mention when not to use the tool or compare with alternatives, though the context is strong.

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. Description adds value by explaining the retrieval operation, scoping, and pairing intent, 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, no fluff. Core function first, then usage context, then scoping. Every sentence contributes meaning.

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 one optional parameter, no output schema, and rich annotations, the description covers all necessary context: two usage modes, scoping, and tool pairing. Nothing missing.

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 fully covers the optional parameter with a clear description. Description adds contextual examples (ticker, address, notes) that help the agent understand typical usage beyond schema.

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

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

Description clearly states it retrieves a value by key or lists all keys when omitted, using specific verbs and resource. Differentiates from siblings 'remember' and 'forget' by naming them and describing their roles.

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

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

Explicitly says 'use to look up context the agent stored earlier' and notes scoping to an identifier. Mentions pairing with remember/forget, but lacks explicit when-not or alternatives beyond sibling names.

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

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

Annotations already indicate readOnly, idempotent, non-destructive. Description adds behavioral details: mark_read flags events read, polling works, and the direct endpoint alternative. No contradictions with annotations.

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

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

Two sentences that front-load the core purpose. Could be slightly tighter but no unnecessary words. Well-structured with key details upfront.

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

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

Given no output schema, the description explains return fields (source, citation_uri, raw payload) and provides context for polling vs direct endpoint. Covers all important aspects for a read-only poll 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%. Description adds meaning beyond schema: explains mark_read effect ('flag returned events read so the next call only shows newer ones'), clarifies filters (type, since). Adds value to 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 specifies exactly what the tool does: 'Pull fired events from your subscription feed' and lists key return fields. It clearly distinguishes from sibling tools like 'list_subscriptions' or 'recent_changes' by focusing on subscription feed alerts.

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

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

Provides guidance on filtering (type, since) and the mark_read flag behavior. Mentions polling works fine and an alternative direct endpoint for scripts/dashboards. Lacks explicit when-not-to-use but overall helpful.

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, idempotentHint, and openWorldHint. The description goes beyond by detailing internal behavior: fan-out to multiple sources (SEC, GDELT→GNews fallback, USPTO), handling of rate limits and soft-fails, and return structure with citation URIs. No contradictions with annotations.

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

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

The description is fairly concise but could be slightly tighter. It efficiently front-loads with example queries and uses parentheticals for fallback behavior. Every clause serves a purpose, though some redundancy (e.g., listing the same fallback in two ways) could be trimmed.

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 sources, fallback, no output schema), the description covers key aspects: sources queried, return structure (changes grouped by source, total_changes, URIs), and parameter behavior. However, it lacks explicit details on the fields within each change object or pagination, which could be inferred from context but not stated outright.

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

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

Despite 100% schema description coverage, the description adds significant value: it explains the 'type' enum's current limitation ('Only "company" supported today.'), provides concrete examples for 'value' (ticker or CIK), and elaborates on 'since' with format details ('ISO date...or relative shorthand') and a recommended default. This goes well beyond the schema definitions.

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

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

The description provides example queries that clearly illustrate the tool's purpose, specifies it is a change feed for companies, and distinguishes it from the sibling tool 'entity_profile', which is explicitly mentioned as the alternative 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 states when to use this tool ('What's new with X' queries) versus alternatives ('Use entity_profile instead when you want the static profile'). It also provides guidance on the 'since' parameter with suggested values ('Use "30d" or "1m" for typical monitoring').

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

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

Annotations provide idempotentHint=true and destructiveHint=false. The description adds critical behavioral detail: persistent vs. 24-hour retention based on authentication, key-value pair structure, and scoping. No contradiction with annotations; description adds significant value beyond structured fields.

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

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

The description is a single, focused paragraph of 4 sentences, efficient and front-loaded with the core action. Could be slightly more structured (e.g., using bullet points for retention rules), but it is compact and informative.

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

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

Given the tool's simplicity (write-only, 2 params, no output schema) and presence of annotations, the description covers key behavioral context (retention, scoping, pairing). The only minor gap is not mentioning success/failure indicators, but for a write tool this is acceptable.

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

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

Input schema covers both parameters with descriptions (100% coverage). The description gives naming conventions and examples ('subject_property', 'target_ticker') but does not add essential semantic constraints beyond schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool saves data for later reuse, uses a specific verb ('Save'), and distinguishes from sibling tools like recall and forget. It provides concrete examples (resolved ticker, target address, user preference) that make the purpose unambiguous.

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

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

The description explicitly advises when to use ('when you discover something worth carrying forward') and mentions alternatives (recall, forget). It also notes scope (scoped by identifier) and retention differences by authentication. Lacks explicit 'when not to use' guidance, but the positive usage context is strong.

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, and non-destructive behavior. Description adds value by noting internal cascading lookups and that it replaces 2-3 manual steps, providing context beyond annotations.

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

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

Well-structured with front-loaded examples and organized by entity type. Slightly verbose but every sentence contributes meaning; minor reduction possible without losing clarity.

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

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

Despite no output schema, description thoroughly explains return values (ticker, CIK, company_name, citation URI for company; RxCUI, ingredient, brand, citation for drug). Covers all aspects for a lookup tool.

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

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

Schema covers 100% of parameters with clear descriptions. Description adds extra context such as auto-disambiguation, accepted input formats, and return fields (e.g., citation URIs), enhancing understanding beyond the schema.

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

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

Description clearly states the tool resolves names to canonical identifiers, provides specific examples (ticker, CIK, RxCUI), and distinguishes from sibling tools by specifying its role as a lookup intermediary.

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 'Use FIRST whenever you have a name but need an ID,' and details supported types and their outputs. Lacks explicit when-not-to-use scenarios but provides sufficient context for correct invocation.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false, indicating safety and non-destructiveness. The description adds valuable detail: it internally calls ai_visibility_check for each entity, returns a ranked list with score, confidence, and signal density. No contradictions found.

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

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

The description is two sentences, front-loading the purpose and benefits immediately. Every sentence adds value: the first says what it does and how, the second gives a concrete use case and describes the output. No wasted words.

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

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

Given no output schema, the description adequately explains the return format (ranked list with score, confidence, signal density). It also describes the internal mechanism (probes with ai_visibility_check). However, it does not elaborate on error cases (e.g., missing API key for anthropic) or timeouts, but that's acceptable for a comparative tool.

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

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

Schema coverage is 100% with descriptions for all four parameters. The description adds context beyond the schema: it clarifies that entities should be 2-8, the first is the subject, and explains the models and _apiKey options. This adds meaning for correct usage.

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, probes each with ai_visibility_check, ranks by score, and surfaces which entity is most/least recognized. The verb 'compare' and resource 'AI visibility' are specific, and it differentiates from sibling tools like ai_visibility_check (single entity) and compare_entities (different 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 provides a concrete use case for competitive AI-marketing audits and an explicit question motivating the tool. It implies when to use (side-by-side comparison over single visibility checks), but does not explicitly state when not to use or mention alternatives like compare_entities. Still, the guidance is clear.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds valuable behavioral context: partial failures, response structure (summary block, per-advisory detail, links, alternative versions), and timing caveat (bundlephobia first measurement 5-30s). 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 fairly long but well-structured: starts with purpose, then usage, response components, ecosystem scope, and fallback. Every sentence is informative. Minor room for trimming but overall efficient.

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

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

Given the tool's complexity (multiple data sources, partial failures, no output schema), the description fully covers what the agent needs: inputs, outputs, failure modes, and scope. It is complete and actionable.

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%. Description adds practical details: clarifies scoped packages accepted and default version behavior (latest when omitted). This goes beyond the schema's descriptions, earning above 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?

Description clearly states it's a composite check for 'should I add this npm package' combining deps.dev and bundlephobia. The verb 'scan_dependency' and resource 'dependency' are specific, and it distinguishes from unrelated sibling tools (e.g., scan_competitor_ai_presence).

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

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

Explicitly says 'Use whenever an agent asks...' and provides concrete queries. Also notes NPM-only scope in v1 and mentions fallback for other ecosystems via deps.dev directly. Provides clear when-to-use and when-not.

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, open-world, idempotent, non-destructive. The description adds crucial behavioral details beyond annotations: embedding model (BGE-base-en), similarity metric (cosine), window size (500-char overlapping), character limit (200K chars truncated and flagged), and the purpose of offsets (allowing agent to verify verbatim quotes). This is excellent transparency.

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

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

Single paragraph with a logical flow: purpose statement, usage scenario, output description, pairing hint, and technical details. Every sentence earns its place; no redundant phrasing. Concise yet comprehensive.

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

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

Given no output schema, the description adequately explains the return (passages with character offsets and similarity scores). Covers technical constraints (model, window size, character limit) and pairing with a sibling. The tool is fully described 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%, so baseline is 3. The description reinforces the text parameter with a clear explanation and size limit, gives example queries for the query parameter, and implicitly defines limit through schema. Adds some value but does not significantly surpass schema detail.

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

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

The description clearly states 'Semantic search INSIDE a fetched record' and gives concrete examples (SEC 10-K, article, tool result). It specifies the output (top-N passages with offsets and similarity scores). The name 'search_within' is well differentiated from siblings like 'ask_pipeworx_grounded' which is explicitly mentioned as a complement.

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 using when the record is too large for the prompt, saving context. Mentions pairing with ask_pipeworx_grounded. Does not explicitly list when NOT to use or alternative sibling tools, but the guidance is clear enough for typical agent selection.

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

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

Annotations already indicate mutable, open-world, idempotent, non-destructive behavior. The description confirms creation and authentication needs but adds no major behavioral context beyond what annotations provide, such as side effects or rate limits for the creation itself.

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 and front-loaded, with each section adding value. It is slightly verbose but efficient given the complexity. Every sentence serves a purpose.

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

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

Despite no output schema, the description covers subscription types, parameters, delivery options, authentication, and limitations comprehensively. It adequately prepares 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%, and the description adds extensive meaning with examples for each type and delivery channel, including type-specific filters, delivery constraints (e.g., phone verification, daily SMS cap), and webhook details. This significantly aids parameter understanding.

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

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

The description clearly states it creates a proactive monitoring subscription to a live-data event stream and returns a new subscription ID. It specifies subscription types and 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 explains when to use (proactive monitoring) and prerequisites (Pipeworx OAuth account, no anonymous/BYO). It provides context on delivery limitations but does not explicitly contrast with alternative tools or state when not to use.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral context: returns category-bucketed example questions with exact tool+argument shape, and explains topic filtering. This is meaningful beyond the annotations.

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

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

The description is slightly long but extremely information-dense, front-loading the purpose and usage. Every sentence serves a purpose, and the structure is logical.

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 role as an onboarding entry point with one optional parameter and no output schema, the description covers everything needed: output format, usage scenarios, and how it fits with sibling tools.

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

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

Schema coverage is 100% with one optional parameter. The description explains the topic parameter with examples and default behavior (full spread), 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?

The description clearly states it is the onboarding entry point for an agent that just connected, returning category-bucketed example questions. It distinguishes itself from sibling tools by being the first tool to use when the agent is unfamiliar with Pipeworx's capabilities.

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 this FIRST when you do not yet know what Pipeworx can do for you' and provides guidance on using with or without the topic argument. Mentions alternatives like ask_pipeworx, entity_profile, compare_entities as meta-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?

Adds value beyond annotations: explains ownership enforcement, deactivation (not deletion), and impact on historical events. No contradiction with annotations.

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

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

Two sentences, no wasted words, action front-loaded. Perfectly concise.

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

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

For a simple 1-param tool with no output schema, the description fully covers ownership, behavior, and lifecycle implications.

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 the lone parameter completely (100% coverage). Description adds minimal but useful context ('by id'). Baseline 3 is appropriate.

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

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

The description clearly states the action ('Cancel a subscription by id') and resource, distinguishing it from siblings 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?

Gives explicit context: ownership enforcement and deactivation behavior. Does not explicitly state alternatives or when not to use, but the context is sufficient.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds significant behavioral context: it uses structured SEC EDGAR + XBRL for financial claims, a grounded pipeline for others, returns verdict with citations, and mentions it replaces 4-6 sequential calls. 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 a single dense paragraph that front-loads the purpose, lists example triggers, explains pathways, and describes return values. Every sentence adds value, though it could benefit from slight structural improvements like bullet points.

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

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

For a tool with two distinct pipelines (financial vs other claims), the description is thorough. It explains what happens for each type, lists return verdicts, and mentions citations. Although there is no output schema, the description sufficiently describes return fields.

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

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

Schema description coverage is 100% with clear parameter descriptions. The tool description adds value by explaining usage contexts for 'tolerance_pct' (e.g., hallucination detection) and providing examples for 'claim'. This goes beyond the schema.

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

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

The description clearly states the tool verifies natural-language claims against authoritative sources, with specific verb 'validate' and examples of triggers. It distinguishes between two pathways (financial vs other claims), making it distinct from sibling tools like 'deep_research' or 'ai_visibility_check'.

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 whenever the agent needs to check whether something a user said is factually correct.' It explains the two pathways (financial vs other claims), providing guidance on use cases, but does not explicitly list when not to use or compare to alternatives.

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