Nsf Awards

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint are all properly set. The description adds behavioral context: the tool makes API calls (external for Anthropic), returns per-model data (score, confidence, signals, raw_response), and requires a BYO key for Anthropic. It does not mention rate limits or data privacy, but the annotations cover safety traits.

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

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

The description is extremely concise: two sentences plus a brief mention of return structure. It front-loads the core action and output, then explains key options in the second sentence. Every sentence adds value without redundancy.

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

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

Given 4 parameters, lack of output schema, and rich annotations, the description is complete. It covers purpose, usage conditions, parameter roles, and return format (per-model score, confidence, signals, raw_response, combined view). No obvious gaps remain for the agent to invoke the tool correctly.

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

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

Schema coverage is 100% with descriptions for all four parameters. The description adds beyond the schema by clarifying the default model, the purpose of _apiKey (passed straight through to api.anthropic.com), and how context helps disambiguate. This extra context raises the score above the baseline of 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's function: probing LLMs for brand knowledge and scoring visibility. It specifies the verb 'probe', the resource (LLMs for business/brand/product/topic), and the output (per-model score 0-100). This clearly distinguishes it from sibling tools like ask_pipeworx or entity_profile, which serve different purposes.

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 concrete use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also explains key conditions: default model is Workers AI Llama-3.3-70b, and Anthropic probing requires providing _apiKey. While it does not explicitly say when not to use it, the context and alternatives are implied by sibling tool 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?

Discloses internal orchestration (picks tool, fills arguments) but doesn't cover authorization, rate limits, or side effects, though the read-only nature is implied.

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

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

Extremely concise: two sentences plus bulleted examples, front-loaded with core purpose.

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

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

Fully describes a simple tool with one parameter and no output schema; examples and orchestration explanation suffice.

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 parameter, but description adds value with example questions illustrating usage 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 it answers questions in plain English by selecting the best tool, distinguishing it from sibling tools like compare_entities and search_awards.

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

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

Provides clear context and examples for when to use, but lacks explicit when-not-to-use or alternative suggestions.

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

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

Annotations (readOnlyHint=true, openWorldHint=true, destructiveHint=false) are consistent. The description adds significant context: it explains the fan-out logic (e.g., crypto+fred+gdelt for BTC bets), the classification step, and the return format (evidence packet + comparison). This goes beyond the annotations to fully disclose behavior.

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

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

The description is relatively long but well-structured and every sentence adds value. It front-loads the main purpose, then details the workflow. Could be slightly tighter but is clear 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?

Covers the core functionality thoroughly: market resolution, classification, fan-out, and output. No output schema is provided, but the description explains what is returned. Missing details on error handling (e.g., invalid slug) but acceptable for the intended use.

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

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

Schema coverage is 100% with descriptions for both parameters. The description reinforces the market parameter examples (slug, URL, question text) and hints at depth behavior (quick vs thorough). This adds practical usage context beyond the schema definitions.

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

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

The description clearly states it researches Polymarket bets by pulling Pipeworx data. It specifies the resource (bet/market) and verb (research), and the examples of inputs make it unambiguous. The tool's purpose is distinct from sibling tools like ask_pipeworx or compare_entities.

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

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

Explicit usage cues: 'Use for "should I bet on X?", "what does the data say...", "is there edge...". Also states it's the core demo product and that agents using it convert better than alternatives, providing strong guidance on when to invoke this tool.

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

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

With no annotations, the description covers expected return data for both types and notes the output includes URIs. It does not mention destructive actions, which is appropriate for a read-only comparison tool.

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

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

Two sentences, front-loaded with purpose and boundaries, 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?

The description gives enough context for the agent to understand usage and output, though without an output schema it could elaborate on return format slightly more.

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 concrete examples (e.g., tickers for company, drug names) and explains how type selects data fields, going 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 compares 2-5 entities side by side, specifies two entity types with distinct data fields, and highlights that it replaces many sequential calls.

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 explains when to use the tool and provides examples for each type, but does not explicitly mention when not to use or alternatives.

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

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

No annotations provided, so description carries burden. States it returns 'the most relevant tools with names and descriptions' but does not disclose search behavior, ranking, pagination, or safety (read-only implied). Adequate but not rich.

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 unnecessary words. First sentence states purpose, second gives usage guidance. Front-loaded and efficient.

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

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

Given 100% schema coverage and no output schema, description covers core purpose and usage. Lacks details on result ranking or output format beyond 'names and descriptions', but serviceable for a search tool.

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

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

Schema coverage is 100% (both params described in schema). Description adds minimal value: 'by describing what you need' maps to query, but limit is already clear. Baseline 3 is appropriate.

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

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

Clearly states 'Search the Pipeworx tool catalog' with a specific verb and resource. Distinguishes from siblings like get_award and search_awards by positioning itself as the first call for tool discovery.

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 the agent to 'Call this FIRST when you have 500+ tools available and need to find the right ones for your task.' Provides clear context and when-to-use guidance.

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

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

With no annotations, description carries full burden. It discloses fetching from multiple sources and returning pipeworx:// URIs. However, it doesn't mention auth requirements, rate limits, or performance traits, slightly reducing 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?

Three concise sentences: first states purpose, second lists contents, third provides guidance. No unnecessary words. Information is front-loaded.

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

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

Given complexity and no output schema, description covers return contents (data sources) and citation URIs. It could mention data freshness or limitations, but overall it sufficiently informs the agent.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by clarifying value as ticker or CIK, explicitly saying names are not supported, and advising to use resolve_entity if only a name is available.

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

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

The description clearly states it returns a full profile of an entity across multiple Pipeworx packs, listing specific data sources (SEC filings, XBRL, patents, news, LEI). It distinguishes itself from siblings like compare_entities and resolve_entity.

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

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

Explicitly states when to use (for a comprehensive profile) and when not (for federal contracts, use usa_recipient_profile). Also clarifies that type only supports 'company' and value must be ticker/CIK, not names, directing to resolve_entity for 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?

No annotations provided. Description only says 'delete' but does not disclose if deletion is permanent, reversible, or has side effects. Minimal behavioral insight.

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

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

Single sentence, no filler, front-loaded with purpose. Every word earns its place.

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

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

Given the simplicity (one parameter, no output schema), the description is largely adequate. Could mention exact match requirement or behavior on missing key, but not critical.

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

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

Schema has 100% coverage for the single parameter. Description does not add extra meaning beyond what the schema's 'Memory key to delete' provides.

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

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

Description clearly states the action (delete) and the resource (stored memory) with the required parameter (key). Distinguishes from sibling tools like '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?

No guidance on when to use this tool versus alternatives, nor any conditions or prerequisites for deletion.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds value by explaining the internal process: fetches page, extracts title/description/key links, outputs standard llms.txt format. No contradiction with annotations.

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

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

Description is concise, front-loaded with purpose, and well-structured. Each sentence adds value without redundancy. Efficient and clear.

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 (2 params, no output schema), the description fully covers purpose, usage, and behavior. It is complete and sufficient for an agent to understand and invoke the tool correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description does not add extensive parameter details beyond the schema, but context on fetching and extracting complements the parameter descriptions. No contradictions.

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

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

Description clearly states the tool generates a production-ready llms.txt file for any URL, specifying the verb (generate), resource (llms.txt), and context (for AI crawlers). It distinguishes from sibling tools like ai_visibility_check and scan_competitor_ai_presence by focusing on file generation.

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

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

The description lists explicit use cases: getting a client's site indexed, drafting for your own project, or auditing competitor visibility. It provides context on when to use but does not explicitly state when not to use or mention 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?

With no annotations, the description transparently discloses return contents: full abstract, project outcomes report (if completed), and PI/awardee info. No side effects or mutability issues.

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 sentence front-loaded with action and resource, no redundant words. 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?

Low complexity tool (1 param, no nesting, no output schema). Description adequately conveys what the tool returns, though could mention behavior if award not found.

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

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

Input schema has 100% coverage with description of award_id. The description adds no extra meaning beyond the schema, meeting the baseline for full coverage.

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

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

The description clearly states the verb 'Fetch' and the resource 'a single NSF award by ID', distinguishing it from siblings like search_awards which returns multiple.

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?

No explicit when to use or not use this tool vs alternatives. It is implied that this is for fetching a specific award by ID, but no mention of search_awards for cases without an ID.

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

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

With no annotations, the description carries full burden. It discloses that feedback is sent, includes content guidelines (no verbatim prompts), and mentions a rate limit (5 per day). It does not detail data handling or response behavior, but the core behavioral traits are covered.

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

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

The description is three sentences, each serving a clear purpose: stating the action, providing usage guidance, and noting a rate limit. It is front-loaded with the verb and purpose, with no extraneous information.

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

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

Given the tool has 3 parameters (one nested object), no output schema, and no annotations, the description covers the essential points: purpose, usage, behavioral constraints, and rate limits. It could mention whether a confirmation or response is given, but overall it is complete for a feedback tool.

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

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

The input schema already provides 100% coverage with detailed descriptions for all parameters, including an enum with descriptions and an optional context object. The description adds minor value by reinforcing usage guidelines, but mostly duplicates schema info.

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: 'Send feedback to the Pipeworx team.' It enumerates specific use cases (bug reports, feature requests, missing data, praise) and is distinct from sibling tools like query or memory tools.

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

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

The description provides explicit when-to-use guidance by listing use cases and includes behavioral guidelines (describe in terms of Pipeworx tools/data, no verbatim prompts). It also mentions a rate limit. It lacks explicit when-not-to-use or alternatives, but the purpose is sufficiently specific.

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

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

Beyond annotations (readOnly, idempotent), description adds crucial detail: data source (CF analytics), no PII, caching behavior (5min-1h). No contradictions detected.

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

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

Efficient paragraph with bullet points, but first sentence could be more front-loaded; overall well-structured without unnecessary words.

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

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

Lacks output schema, only vaguely mentions return values (top tools, packs, call volume). For a simple tool it's adequate but not fully complete for an agent to parse the response.

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 its property description already explains window semantics. The tool description adds no new parameter meaning beyond what's in 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 trending tools, packs, and call volume over a window, with specific use cases that distinguish it from siblings like discover_tools.

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

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

Provides three explicit use cases (discovering hot data, confirming canonical choice, aligning use case) but does not mention when not to use or contrast with alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that the tool returns ranked opportunities with suggested trade direction and reasoning, but does not disclose potential rate limits, data freshness, or error conditions. It is adequate but not extensive.

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

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

The description is well-structured with a clear purpose statement followed by a bulleted explanation of the two modes. It is detailed yet each sentence adds value, though it could be slightly more concise without losing information.

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

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

Given no output schema, the description gives a high-level summary of returns ('ranked opportunities with suggested trade direction + reasoning') but lacks specifics on the exact JSON structure or fields. It also does not mention error handling or edge cases. Acceptable but not fully complete.

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

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

Schema coverage is 100% and each parameter has a description with examples. The description adds meaningful context by explaining the behavioral logic of each mode (e.g., event walks child markets, topic searches across events), which goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool's purpose: finding arbitrage opportunities via monotonicity violations on Polymarket. It specifies two distinct modes ('event' and 'topic'), which provides specific verb+resource clarity and differentiates internal usage patterns.

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

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

The description explains when to use each mode (event for single event, topic for cross-event) and gives concrete examples. It highlights why cross-event mode is necessary for separate events, but does not explicitly compare with sibling tools or state when not to use the tool.

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

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

Annotations already provide readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds valuable behavioral context: it uses a lognormal model from FRED and live coinpaprika price, groups by asset, fetches price history once, and computes model probability per market. 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 fairly concise at three sentences, each serving a purpose: statement of function, technical detail, and output description. However, the second sentence is somewhat long and could be split for clarity, 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 complexity of the tool (external data sources, model), the description covers purpose, algorithm, and output (top N with edge and direction). No output schema exists, but description adequately describes return values. Annotations fill remaining safety context.

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

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

Schema coverage is 100% with all three parameters described. The description does not add additional semantic meaning beyond the schema; it merely restates the parameters' purposes in context of the algorithm. 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 scans high-volume Polymarket markets, finds where Pipeworx data disagrees with market price, and returns top N ranked by edge magnitude with suggested trade direction. It distinguishes itself from siblings like polymarket_arbitrage and bet_research by its specific function of discovering opportunities.

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 it is built for the 'what should I bet on today' question, helping agents/users discover opportunities without paging through hundreds of markets. While it does not explicitly say when not to use it, it provides clear context and implies its primary use case.

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

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive traits. The description adds behavioral details: returns leg-by-leg prices in raw probability (0-1) and spread in percentage points (Kalshi minus Polymarket). It also explains the typical spread range (2-25pp). 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 slightly verbose but well-structured. It front-loads the purpose and value proposition, then explains the two modes, and ends with return format. Every sentence adds value. Could be slightly more concise (e.g., trim 'TWO MODES' detail), but overall effective.

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

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

Despite no output schema, the description explains the return format (leg-by-leg prices and spread) adequately. It covers both modes and mentions the typical spread range. For a read-only tool with three optional parameters, this is complete. Minor gap: does not mention that both explicit tickers can be provided simultaneously, but it's implied by 'overrides'.

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

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

Schema has 100% description coverage with each parameter documented. The description adds further meaning by explaining the relationship between parameters: topic provides pre-mapped shortcuts, while explicit tickers override the topic-mapped side. It clarifies that both explicit tickers can be used together for custom pairings, which is not obvious from schema alone.

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

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

Description clearly states it is a cross-venue spread tool between Kalshi and Polymarket. It defines the core function: comparing prices of same-resolving questions on two venues to identify arbitrage signals. It distinguishes itself with two modes (topic shortcuts and explicit tickers) and explains the reason for the spread (different participant pools). This provides a specific verb-resource combination and differentiates from siblings 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?

Explicitly describes two modes of operation and when to use each: pre-mapped topics for convenience, and explicit tickers for custom pairings. It gives context on why the spread exists (2-25pp difference). However, it does not mention when not to use this tool or provide alternatives (e.g., maybe a single-venue tool for simpler queries). Still, the guidance is clear and actionable.

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

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

The description clearly states this is a retrieval operation with no destructive effects. It explains the behavior when key is omitted (list all). With no annotations, the description adequately discloses core behavior.

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

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

The description is two sentences, front-loaded with the action, and contains no unnecessary words. Every sentence adds value.

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

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

For a simple tool with one optional parameter and no output schema, the description is fairly complete. It could mention error handling for missing keys, but that is not critical.

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

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

The schema describes the 'key' parameter well, and the description adds context: omitting the key lists all memories. This enhances understanding beyond the schema.

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

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

The description clearly states the tool retrieves a memory by key or lists all memories when key is omitted. It distinguishes itself from sibling tools like 'remember' (store) and 'forget' (delete).

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

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

The description advises when to use the tool ('Use this to retrieve context you saved earlier...') and implies not to use it for storing or forgetting. However, it does not explicitly mention 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?

With no annotations, the description fully carries the behavioral disclosure. It details the fan-out to SEC EDGAR, GDELT, USPTO in parallel for company type, explains accepted formats for 'since' (ISO date or relative), and describes the return structure (structured changes, total_changes count, pipeworx:// 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 concise: four sentences that pack the purpose, fan-out behavior, parameter details, and usage guidance. It is front-loaded with the core purpose ('What's new about an entity...') and every sentence adds value without redundancy.

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

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

Given the tool's complexity (parallel sources, multiple parameter formats), the description is complete. It covers the entity type limitation, return structure, and provides a usage tip. Without an output schema, the description suffices by describing what the tool returns.

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

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

The input schema has 100% description coverage, but the description adds significant meaning: it clarifies that 'type' currently only supports 'company', gives examples for 'value' (ticker or CIK), and explains the format and default for 'since' (ISO or relative, with monitoring suggestion). This goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool's purpose: finding what's new about an entity since a given time. It specifies the resource (entity) and operation (recent changes), and distinguishes from siblings by noting its use for 'brief me' or change-monitoring workflows, which is distinct from other tools like compare_entities or entity_profile.

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

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

The description provides explicit use cases: 'Use for brief me on what happened with X or change-monitoring workflows.' It also gives a practical tip for the 'since' parameter ('Use 30d or 1m for typical monitoring'). While it doesn't explicitly state when not to use it, the context and sibling differentiation make the guidance 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?

No annotations exist, so the description carries full burden. It discloses persistence behavior (authenticated vs. anonymous sessions) and storage of key-value pairs, though it omits limits on key/value size or overwrite semantics.

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

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

Two concise sentences. First sentence states the action, second sentence adds usage context and persistence distinctions. No fluff.

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

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

For a simple tool with two parameters and no output schema, the description covers purpose, usage, and persistence. Minor gaps: no mention of overwrite behavior or size limits, but these are not critical.

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

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

Input schema covers both parameters with descriptions (100% coverage). The description adds example keys and values but does not provide meaningful extra information beyond the schema.

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

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

The description clearly states the tool stores a key-value pair in session memory and enumerates specific use cases (intermediate findings, user preferences, context). It distinguishes from siblings like 'recall' and 'forget'.

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

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

The description provides explicit use cases and persistence differences (authenticated vs. anonymous). However, it does not mention when not to use or alternatives among siblings.

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

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

No annotations are provided, so the description carries full burden. It describes the mapping behavior and return values (IDs and URIs), but does not disclose any other behavioral traits (e.g., read-only nature, rate limits, error handling).

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

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

The description is concise (3 sentences) and well-structured: purpose, supported types with examples, return value, and benefit. 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?

Given no output schema, the description adequately explains the return format (IDs and URIs). It covers the core functionality but could mention potential error cases or limitations. For a simple 2-param tool, it is fairly complete.

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

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

Schema coverage is 100%, and the description adds valuable examples and context for each parameter (e.g., ticker vs CIK for company, brand vs generic for drug), going beyond the schema's own 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 resolves entities to canonical IDs for two specific types (company and drug), with explicit input-to-output mappings. It distinguishes itself from sibling tools by claiming it replaces multiple lookup calls.

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 when to use the tool (single call replacing 2-3 lookups) and gives examples of valid inputs. However, it does not explicitly mention when not to use it or compare to specific siblings like search_awards.

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=false. Description adds behavioral details: probes each entity, ranks by score, returns ranked list with score, confidence, signal density. Also mentions internal use of ai_visibility_check. 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?

Three sentences that front-load purpose, then detail usage example and output. Every sentence adds value with no redundancy or fluff.

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

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

Given complexity (4 params, no output schema), description adequately explains input constraints and output format (ranked list with score, confidence, signal density). Could be enhanced with an example return structure, but sufficient for an agent.

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

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

Schema description coverage is 100%, but description adds context beyond schema: entities array limited to 2-8, first entry treated as subject, explanation of models default and API key requirement. Provides meaningful additional semantics.

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

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

Description clearly states it compares AI visibility across multiple entities, probes with ai_visibility_check, ranks by score, and surfaces most/least recognized. Verb+resource is specific, and it distinguishes from siblings like ai_visibility_check (single entity) and compare_entities.

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

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

Explicitly states usefulness for competitive AI-marketing audits with an example question. Provides context for when to use (side-by-side comparison) but does not explicitly state when not to use or list alternatives. Clear enough for an agent.

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

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

Description adds significant behavioral context beyond annotations: fans out across two services, returns summary block with specific fields, handles partial failures, and mentions bundlephobia delay. No contradictions with annotations.

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

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

The description is dense but front-loaded with the core purpose. Could be broken into clearer sections but is efficient and every sentence adds value.

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

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

Given no output schema, the description thoroughly explains the return structure, error handling (sources_failed), and service interactions. Covers complexity well.

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. Description adds value by mentioning scoped packages accepted and default behavior for version. Slightly above baseline.

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

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

The description clearly states it is a composite check for npm packages covering license, advisories, version history, and bundle size. It distinguishes from siblings by specifying the npm ecosystem and noting that other ecosystems fall under a separate tool.

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

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

Explicitly says when to use: whenever an agent asks 'is X safe / popular / small' or 'what does adding lodash cost me'. Also notes limitations like NPM only in v1 and partial failures gracefully degrading.

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?

With no annotations, the description carries the full burden. It states the return fields (title, PI, awardee, amount, dates, program) but does not disclose pagination behavior, rate limits, or what happens with no filters. This is adequate but not thorough.

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: the first lists purpose and filters, the second lists return fields and an alternative. It is concise and front-loaded, with 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 the 10 parameters and no output schema, the description covers purpose, filters, return fields, and an alternative tool. It could mention pagination behavior, but overall it is relatively 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 description coverage is 100%, so the schema already documents each parameter. The description adds context like 'keyword matches title/abstract' but does not provide significant additional meaning beyond the schema.

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

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

The description starts with 'Search NSF awards' which clearly states the specific verb and resource. It lists filter criteria and distinguishes from sibling tool get_award by mentioning that get_award provides full abstract and outcomes report.

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 get_award for full abstract + outcomes report,' providing clear context for when to use this tool versus the alternative. It does not explicitly state when not to use, but the guidance 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?

With no annotations, the description carries the full burden. It transparently describes the return value (verdict, structured form, actual value with citation, percent delta), the current v1 limitation to company-financial claims, and the tool's read-only nature. It does not mention rate limits or authentication, but for a single-purpose tool, this is adequate.

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

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

The description is concise with 3-4 sentences, no superfluous text, and effectively front-loads the core action ('Fact-check a natural-language claim'). Each sentence adds value: scope, return values, and efficiency benefit.

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 single required parameter, no output schema, and simple context signals, the description provides complete information for an agent to understand and invoke the tool. It explains inputs, outputs, and purpose fully without needing additional context.

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

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

The single parameter 'claim' has a descriptive schema with examples, achieving 100% coverage. The description adds context about expected input format and provides two concrete examples ('Apple's FY2024 revenue...', 'Microsoft made about $100B...'), which goes beyond the schema definition.

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 fact-checks natural-language claims using authoritative sources, specifies scope (company-financial for public US companies) and data sources (SEC EDGAR + XBRL). This distinguishes it from siblings like compare_entities or search_awards, which have different purposes.

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 notes it replaces 4-6 sequential agent calls, indicating when to use for efficiency. However, it does not provide explicit when-not-to-use conditions or mention alternative sibling tools, though the purpose is clear enough for an agent to infer.

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