Gmail

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

The description discloses that Pipeworx 'picks the right tool, fills the arguments, and returns the result,' indicating autonomous behavior. Since no annotations are provided, the description carries the full burden; it successfully conveys the tool's automatic orchestration without misleading. No contradictions with annotations (none present).

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) and front-loaded with the core purpose. It includes examples for clarity. One could argue the first sentence could be more direct, but overall it is efficient and well-structured.

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

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

Given the tool's simplicity (one parameter, no output schema, no nested objects), the description is complete enough. It explains how the tool works and what to expect. However, it could mention that the result is a text answer or that the tool may use external APIs, but this is not essential for basic use.

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

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

Schema description coverage is 100% with one parameter 'question' described as 'Your question or request in natural language.' The description adds value by explaining that the question should be in plain English and providing examples, but the schema already clearly defines the parameter. Thus, the description reinforces but does not significantly extend beyond the schema.

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

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

The description clearly states the tool's purpose: 'Ask a question in plain English and get an answer from the best available data source.' It uses specific verbs ('ask', 'get an answer') and resources ('best available data source'). The tool is well-distinguished from siblings like discover_tools (which lists tools) and recall (which retrieves memories) by emphasizing natural language querying and automatic tool selection.

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

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

The description provides clear usage guidance: 'No need to browse tools or learn schemas — just describe what you need.' It includes three concrete examples showing typical queries. However, it does not explicitly state when not to use this tool or mention alternatives (e.g., when to use gmail_search instead for email-specific queries).

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 behavior beyond annotations: it resolves the market, classifies the bet type, fans out to appropriate packs, and returns an evidence packet with comparison. No contradiction with annotations (readOnlyHint, openWorldHint, destructiveHint).

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 contains some verbose marketing language ('core demo product — agents that get bet-relevant context here convert better'). Still, every sentence adds value, and the 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 no output schema, the description fully explains the output (evidence packet plus simple market-vs-model comparison). Inputs, processing steps, and use cases are all covered, making it complete 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 coverage is 100%, but the description adds meaning: explains that market can be slug, URL, or question text, and depth has two levels. This enhances the agent's understanding of parameter 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: researching a Polymarket bet by pulling relevant Pipeworx data. It specifies inputs (market slug, URL, or question text) and outputs (evidence packet plus comparison), making it distinct from sibling tools.

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

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

Explicit usage scenarios are provided: 'Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?"'. This clearly guides the agent 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 carries full burden. It discloses data sources (SEC EDGAR, FDA) and return format (paired data + URIs), but does not mention side effects, permissions, rate limits, or error handling. Adequate but not exhaustive.

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 list. It front-loads the main action and efficiently conveys purpose, data, and return type. 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 only two parameters and no output schema, the description covers the key aspects: purpose, parameter usage, return type, and efficiency gain. It could mention that results are paired, but overall it's complete for the tool's complexity.

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

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

Schema coverage is 100%, so baseline 3. The description adds value by explaining the specific data fields for each type and that values are tickers/CIKs or drug names, going beyond the schema's enum and description.

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 compares 2-5 entities side by side, specifying the resource (entities of type company or drug) and the specific data fields returned for each type. It distinguishes itself from sibling tools by focusing on batch comparison, replacing 8-15 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?

The description indicates when to use the tool by noting it replaces sequential agent calls, implying efficiency. It provides clear guidelines for the type parameter. However, it does not explicitly state when not to use it or mention alternatives, but the context of siblings makes it sufficiently 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 provided, but description discloses that it performs a search and returns tool names and descriptions. It implies a non-destructive, read-only operation. However, it does not mention edge cases like no results or 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?

Three sentences, all essential: purpose, return value, and usage guidance. No fluff.

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

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

Given no output schema, the description adequately explains what the tool returns ('most relevant tools with names and descriptions'). It is complete for a search tool with simple input parameters.

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 description adds value by explaining that query is a natural language description and gives examples. Limit parameter is documented with defaults and max. Description does not add much beyond schema but examples are helpful.

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 searches the tool catalog by describing what you need, returns relevant tools, and should be called first when many tools are available. The verb 'Search' and resource 'tool catalog' are specific, and it distinguishes itself as a discovery 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 'Call this FIRST when you have 500+ tools available', providing clear guidance on when to use this tool and its purpose in the workflow.

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 the full burden. It discloses that the tool performs a read operation returning citation URIs, bundles multiple sources (replacing 10-15 sequential calls), and excludes federal contracts. While it doesn't mention pagination or rate limits, the read-only nature and output format are clearly stated, giving strong transparency.

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

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

The description is concise, front-loads the main purpose in the first sentence, then lists data types and alternatives. Every sentence provides unique value, with no wasted words. It is optimally structured for quick agent comprehension.

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

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

Given the simple input schema (2 parameters, fully described) and no output schema, the description sufficiently covers what the tool does, what data it returns, and how to use it. It also addresses edge cases (federal contracts, name resolution). The description is complete for the tool's complexity.

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

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

The input schema already has 100% coverage for both parameters. The description adds significant value by explaining that the 'type' parameter is currently limited to 'company', and the 'value' parameter accepts tickers or CIKs and recommends resolve_entity for names. This 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 that the tool aggregates a full entity profile across multiple Pipeworx packs, enumerates the specific data types included (SEC filings, XBRL financials, patents, news, LEI), and explicitly contrasts with the sibling tool usa_recipient_profile for federal contracts. This provides a specific verb+resource and distinguishes it from alternatives.

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

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

The description explicitly tells when to use this tool (for a comprehensive entity profile) and when not to (for federal contracts, use usa_recipient_profile). It also advises that if only a name is available, resolve_entity should be used first. This 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 are absent, so the description must carry full burden. It only states 'Delete', which implies mutation, but no details on side effects, authorization needs, or whether deletion is permanent. The sibling 'forget' suggests memory management, but the description lacks behavioral depth.

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, concise and front-loaded. No wasted words, but could be slightly more informative without sacrificing 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 simple tool (1 required param, no output schema), the description is minimally adequate. However, it lacks information about return values, error handling, and behavioral context that would help an agent use it correctly.

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

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

Schema coverage is 100% with a single parameter 'key' described as 'Memory key to delete'. The description adds no extra 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 the verb 'Delete' and the resource 'stored memory by key', which is specific. It distinguishes from sibling tools like 'remember' (store) and 'recall' (retrieve), though it doesn't explicitly contrast them.

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

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

No guidance on when to use this tool vs alternatives like 'remember' or 'recall'. It doesn't state prerequisites or conditions for deletion, such as whether the key must exist.

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, so description carries full burden. It states returns full message details, which is adequate but doesn't disclose potential rate limits, authentication requirements, 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?

Two sentences, no filler. Front-loaded with purpose, followed by return details. 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 no output schema, description could mention return structure or pagination. But for a simple retrieval tool with good schema, it is minimally complete.

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

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

Schema coverage is 100%, so baseline is 3. Description adds no additional meaning beyond what schema provides for parameters. It mentions headers, snippet, body, labels but doesn't tie to format 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?

Description clearly states it retrieves a specific Gmail message by ID, listing included details. It uses specific verb 'Get' and resource 'Gmail message', distinguishing it from siblings like gmail_list_messages and gmail_search.

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

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

No explicit guidance on when to use vs alternatives. Implies use when you have a known message ID, but doesn't mention when to use other tools for listing or searching.

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 are empty, so description carries full burden. It discloses that both system and user-created labels are returned. However, it does not mention any side effects, rate limits, or other behavioral traits beyond the basic function.

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 concise sentence that conveys all necessary information without extraneous words. It is front-loaded with the main purpose.

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

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

Given zero parameters and no output schema, the description is sufficient for the tool's simplicity. It covers what labels are returned. No additional context is 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?

The schema has no parameters, so there is nothing to explain. The description adds value by clarifying what the tool returns (all labels including system ones), which is useful context beyond the empty 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 all labels in the user's Gmail account, specifying both system labels and user-created labels. It differentiates from siblings by focusing solely on label listing, which is distinct from other Gmail tools that deal with messages or sending.

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 indicates usage when labels need to be enumerated. No explicit when-not or alternatives are given, but the sibling list shows other Gmail tools for messages and search, making it clear this is for labels only.

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 are empty, so the description must convey behavior. It states it returns message IDs and thread IDs but does not mention whether results are paginated (though page_token is in schema), rate limits, or that it only accesses inbox. Adequate but not detailed.

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, straightforward and front-loaded with main action. Could be slightly more structured but 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 should clarify return format; it does say 'message IDs and thread IDs' but lacks detail on the structure (e.g., array of objects). Complexity is low, so 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?

Schema coverage is 100% and descriptions are clear, so the description adds minimal extra value. It does not elaborate on default behavior when no query is provided or the impact of max_results.

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

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

The description clearly states it lists messages in the user's Gmail inbox, with optional filtering and return of IDs. It distinguishes from siblings like gmail_get_message (which gets a single message) and gmail_search (which likely has different scope or output).

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

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

The description mentions optional filtering with a search query but does not explicitly state when to use this tool versus alternatives like gmail_search. No guidance on when not to use it or prerequisites.

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 provided, the description carries the full burden. It discloses that the tool supports operators like from:, to:, etc., which is helpful for understanding query capabilities. However, it does not mention whether the search is case-insensitive, whether it respects user permissions, or that it may return partial results if max_results is set. These are minor omissions.

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, concise and front-loaded with the core purpose. The second sentence adds useful examples. However, it could be slightly more structured (e.g., bullet points) but is still 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 is a search with 2 parameters, no output schema, and no nested objects, the description is fairly complete. It explains the query syntax and parameters. The lack of return value description is acceptable since no output schema exists, but mentioning typical fields returned could add value.

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 both parameters are described in the schema. The description adds value by listing example operators but does not provide additional semantics 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 states 'Search Gmail messages' which identifies the verb (search) and resource (Gmail messages). It distinguishes from sibling tools like gmail_list_messages (which lists without search syntax) and gmail_get_message (which retrieves a single message). The mention of Gmail query syntax further clarifies the specific capability.

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 when to use this tool (when search syntax is needed) but does not explicitly state when not to use it or provide alternatives. Given siblings like gmail_list_messages and gmail_get_message, explicit guidance on choosing between them would improve this dimension.

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 are empty, so description carries full burden. It does not disclose that sending is a write operation with potential side effects (e.g., email leaves the account, rate limits, draft handling). No mention of irreversible actions or required scopes.

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 waste. Could add sibling differentiation or behavior notes without becoming 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 and no annotations, description is insufficient. Does not explain return values (message ID, success indication), error conditions (invalid email, attachment limits), or authentication requirements.

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 no extra meaning beyond the schema; e.g., 'cc' is already described as 'CC recipients (comma-separated email addresses)'. The description does not explain format constraints or optionality 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 verb 'Send' and resource 'email from the authenticated Gmail account'. It distinguishes from sibling tools which list or search messages, but could more explicitly contrast with gmail_search or gmail_list_messages.

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 like gmail_get_message (reading) or gmail_search (finding messages). No prerequisites or context about authentication or sending limitations are provided.

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

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

The description discloses rate limiting ('5 messages per identifier per day') and cost ('Free'), but lacks annotations for further behavioral cues. It does not explicitly state non-destructiveness or idempotency, though the tool is inherently non-destructive. The disclosure is adequate but not comprehensive.

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: two sentences plus a rate limit and cost mention. All information is front-loaded and relevant, with no superfluous content.

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

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

The description covers the tool's purpose, usage, constraints (rate limit, message format), and examples of content types. For a simple feedback tool, no gaps are evident, even without an output schema or annotations.

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 descriptive parameter fields. The description adds value by providing formatting guidance ('Be specific... 1-2 sentences typical, 2000 chars max') and contextual hints for usage, which go 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 'Send feedback to the Pipeworx team' and lists specific use cases (bug reports, feature requests, missing data, praise). This distinguishes it from sibling tools, none of which serve a feedback 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 explicitly states when to use ('Use for bug reports, feature requests, missing data, or praise') and provides a rule ('do not include the end-user's prompt verbatim'). It also mentions rate limiting. It does not explicitly exclude other uses, 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 indicate read-only, open-world, and non-destructive behavior. The description adds substantive behavioral details: it checks monotonicity, walks child markets in single-event mode, searches across events in topic mode, and returns ranked opportunities with reasoning. No contradictions with annotations. A 5 would require more on error handling or limits, but four is warranted.

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 tightly written with no fluff. It front-loads the purpose, uses bold labels for modes, and packs relevant examples into short sentences. Every sentence adds value, making it both comprehensive 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 the tool's complexity (two modes, no output schema), the description covers purpose, usage, and behavioral details thoroughly. It explains the cross-event scenario and indicates return value (ranked opportunities with reasoning). A 5 would require mention of output structure, but four is appropriate as the information is sufficient for effective use.

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

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

Input schema provides descriptions for both parameters with examples, achieving 100% coverage. The tool description enhances semantics by explaining the mode each parameter triggers and the underlying logic (e.g., event walks child markets, topic searches across events). This adds meaningful context beyond the schema.

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

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

The description clearly states the tool's purpose: finding arbitrage opportunities on Polymarket by checking monotonicity violations. It identifies two distinct modes (event and topic) and provides specific verb-resource combinations. The tool is clearly differentiated from siblings like 'polymarket_edges' and 'bet_research' by its focus on arbitrage detection.

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

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

The description explicitly explains when to use each mode with concrete examples, such as the cross-event mode catching cases where Polymarket splits outcomes into separate events. It provides context without explicitly stating when not to use or comparing to sibling tools, but 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 adds substantial behavioral detail beyond annotations: it explains the V1 model (lognormal from FRED + live coinpaprika price), the process (scans top markets, groups by asset, fetches price history once, computes model probability, ranks by |edge|), and the output (top N with suggested trade direction). No contradictions with annotations (readOnlyHint, openWorldHint, destructiveHint false).

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

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

The description is a single, well-structured paragraph that front-loads the main purpose. Each sentence adds value, and there is no redundancy or unnecessary detail. It is concise yet informative, earning a top score.

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 value (top N ranked by edge magnitude with suggested trade direction). It covers inputs, process, and model details, making the tool fully understandable for an agent. The description is complete for the tool's complexity.

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

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

Schema coverage is 100%, so the baseline is 3. The description does not add extra meaning beyond what the schema already provides for parameters (limit, window, min_edge_pp). It mentions their roles in the process but not additional semantics. Therefore, a 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's purpose: scanning high-volume Polymarket markets to find where Pipeworx data disagrees most with market price. It specifies the verb (scan), resource (Polymarket markets), and unique contribution (disagreement with Pipeworx data). This effectively distinguishes it from sibling tools like polymarket_arbitrage and validate_claim.

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 the tool is built for the 'what should I bet on today' question, providing clear use context. However, it does not explicitly state when not to use this tool or mention alternatives among siblings. Still, the context is strong enough for an agent to infer appropriate usage.

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

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

No annotations provided, so description must disclose behavior. It clearly states that omitting key lists all memories, and that memories persist across sessions. No contradictions.

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

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

Two concise sentences with no wasted words. Front-loaded with action and resource, then clarifies behavior.

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?

Simple tool with one optional param and no output schema. Description covers all needed info for invocation. Could mention return format (e.g., string or JSON), 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 description coverage is 100%, so baseline is 3. The description adds context that omitting the key lists all memories, which is not in schema. No further parameter details 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?

Description specifies verb 'retrieve' and resource 'memory', and distinguishes between retrieving a specific key and listing all. It also differentiates from siblings like 'remember' and 'forget' by focusing on retrieval.

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

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

Explicitly states when to use the tool: 'Retrieve context you saved earlier.' However, does not explicitly mention when not to use it or compare with siblings, though the contrast with 'remember' and 'forget' is implicit.

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 description must compensate. It discloses parallelism, supported formats, and return structure (structured changes + total_changes count + URIs). Missing details on rate limits or authentication, but for a read operation it is sufficiently transparent.

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

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

Description is concise, front-loaded with purpose, and every sentence adds necessary information. 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?

Despite no output schema, description covers return format and workflow context. With 3 parameters fully described and behavioral details, it is complete for an agent to select and invoke correctly.

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

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

Schema coverage is 100%, baseline 3. Description adds value: clarifies 'since' formats (ISO date, relative like '7d', '30d', '3m', '1y') and suggests typical usage ('Use "30d" or "1m"'). Also explains 'type' is limited to 'company' and 'value' can be ticker or CIK.

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: 'What's new about an entity since a given point in time.' It specifies entity type 'company' and enumerates data sources (SEC EDGAR, GDELT, USPTO). This differentiates it from sibling tools like entity_profile or compare_entities.

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

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

Description provides explicit use cases: 'brief me on what happened with X' or 'change-monitoring workflows.' It also explains acceptable formats for 'since' and implies when to use (monitoring). However, it does not explicitly state when not to use or provide alternative tools.

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

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

No annotations provided, but description discloses behavioral traits: persistence depends on authentication status ('Authenticated users get persistent memory; anonymous sessions last 24 hours'). This adds useful context beyond the input schema.

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

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

Two sentences, front-loaded with the core action. 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 no output schema and simple parameters, the description covers the essential behavioral aspects (persistence, session type) and usage context. Could mention data size limits or overwrite behavior for full completeness.

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% (both parameters described in schema). The description adds value by clarifying the purpose of the tool but doesn't add new semantic details beyond what the schema already provides.

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

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

The description clearly states 'Store a key-value pair in your session memory' with a specific verb ('store') and resource ('session memory'). It distinguishes itself from siblings like 'recall' (retrieval) and 'forget' (deletion).

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

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

The description explains when to use the tool: 'save intermediate findings, user preferences, or context across tool calls.' However, it does not explicitly state when not to use it or mention alternatives for different storage needs.

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 full burden. It discloses it is a single call, accepts multiple input types, and returns specific fields. For a read-only resolution tool, it is fairly transparent, though it could mention if data is real-time or cached.

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, no redundant information. Efficient and well-structured.

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

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

For a simple 2-parameter tool with no output schema, the description covers input, output, and use case. It could be improved by clarifying if multiple matches are possible, but overall it is complete enough.

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% description coverage. The description adds context by specifying 'v1: type="company"' and providing examples of accepted values (e.g., 'AAPL', '0000320193', 'Apple'), which adds 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?

Description clearly states it resolves an entity to canonical IDs, specifying the entity type (company) and accepted input formats (ticker, CIK, name). It also lists the return fields (ticker, CIK, name, resource URIs). This is specific and distinguishes 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?

The description mentions it replaces 2-3 lookup calls, implying efficiency benefits. While it does not explicitly state when not to use or list alternatives, the context of sibling tools (mostly Gmail and memory) makes its purpose 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?

With no annotations provided, the description carries full burden. It discloses the tool returns a verdict, extracted structured form, actual value with citation, and percent delta. It also specifies the source and scope. While it doesn't mention non-destructiveness or rate limits, it is sufficiently transparent for a read-only validation 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?

The description is two sentences with no redundant information. It front-loads the main purpose and then adds essential details about supported claims and the return value. 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 one parameter and no output schema, the description covers the purpose, supported claim types, sources, return values, and even performance benefit. It is complete enough for an agent to correctly select and invoke the tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by providing examples ('Apple's FY2024 revenue was $400 billion') and specifying the expected claim types, which goes beyond the schema description.

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 against authoritative sources, specifically company-financial claims from US public companies. It lists the supported metrics and sources (SEC EDGAR + XBRL), distinguishing it from any siblings, none of which are claim-verification 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 explicitly says 'v1 supports company-financial claims (revenue / net income / cash for public US companies)', which tells the agent when to use it. It also mentions it replaces 4-6 sequential calls, implying efficiency benefits. However, it does not explicitly state when not to use it or list alternatives.

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