queryquarry

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

Annotations already declare readOnlyHint=true, so safety is conveyed. The description adds value by enumerating the specific information returned (tier, status, rate limit, usage this hour), which is useful behavioral context beyond the annotation. No contradictions.

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

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

The description is a single, front-loaded sentence that lists all key information succinctly with no filler words. Every word contributes meaning.

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

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

For a no-parameter, read-only tool with annotations and no output schema, the description covers the essential return values (tier, status, rate limit, usage this hour). It is complete for understanding the tool's purpose and output without extra detail.

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

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

The input schema has zero parameters, so the baseline is 4. There is no parameter information needed; the description properly focuses on what the tool reports rather than on inputs.

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

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

The description uses a specific verb ('Check') and resource ('subscription tier, status, rate limit, and usage this hour'), clearly stating what the tool does. It is distinct from sibling tools like get_candidate or get_corpus_stats, which focus on other data. No ambiguity exists.

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 the tool is for checking subscription/usage context, which is clear and useful for deciding when to call it. It does not explicitly name alternatives or exclusions, but sibling tools are unrelated, so the intended context is clear without further guidance.

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

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

Beyond the readOnlyHint annotation, the description adds substantial behavioral context: it stays anonymous (no name, no contact, withheld employer names/dates/graduation years) and counts toward the hourly/daily reveal limit. No contradiction with annotations.

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

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

The description is three sentences long, with the primary action front-loaded in the first sentence. It includes only essential details (evaluation scope, anonymity, reveal limit, contact alternative) with no redundancy or unnecessary elaboration.

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 evaluation content, anonymity constraints, rate-limit implications, and the contact alternative, making it sufficiently complete for an AI agent to understand the tool's role. The only notable gap is parameter semantics, which is already scored separately, so overall context remains strong given the 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?

The schema has two required parameters (candidate_id, resume_id) with zero description coverage, and the tool description does not explain what these IDs mean, how they differ, or their expected format. Given the 0% schema coverage, the description needed to compensate but failed to do so.

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

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

The description uses a specific verb 'Evaluate' and identifies the resource as 'one candidate in depth', enumerating the fields covered (skills, summary, seniority, experience, education). It also distinguishes itself from siblings by explicitly stating it stays anonymous and directing users to request_contact for actually reaching someone.

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 clearly names request_contact as the alternative when the goal is to reach someone, and it notes the reveal limit, which implies usage context. However, it does not explicitly contrast with list-oriented siblings like search_candidates, so the guidance is clear but not exhaustive.

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, so no contradiction. The description adds valuable context: status meanings (sent/accepted/declined), consequences of acceptance, and an additional hire outcome feature. It doesn't describe edge cases or return format, but the addition is substantive.

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, tightly packed with information: purpose, statuses, identification method, and additional hire outcome. No redundancy; front-loaded with the primary verb+resource.

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 lookup tool with no output schema, the description covers the tool's behavior, possible outcomes, and additional context (hire outcome, intro email). It doesn't address error conditions, but that's not critical for basic usage. The reference to shared_contact provides useful cross-tool 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 provides no descriptions (0% coverage), so the description must compensate. It states either contact_id or code can be used for identification, which adds meaning beyond the schema. However, it doesn't explain parameter formats or specify whether exactly one is required, leaving some ambiguity.

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

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

The description specifies the exact action ('Check the status of a contact request you sent'), defines the possible statuses, and differentiates from siblings like request_contact and report_contact_outcome by focusing on status checking. It also clarifies how to identify the request (by contact_id or code).

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

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

It clearly implies when to use (after sending a contact request) and provides context for interpreting 'accepted' status (see shared_contact, expect intro email). It lacks explicit alternatives or exclusions, but the context is unambiguous compared to sibling tools.

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

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

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds value by specifying what stats are included ('counts, top skills/locations'), giving the agent a concrete expectation of the return data. 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?

A single, front-loaded sentence with no filler. It communicates the action, resource, and content types in under 15 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?

For a zero-parameter tool with no output schema, the description provides a sufficient high-level summary of what the tool returns. It could specify which counts (e.g., total candidates) or return format, but the stated scope is adequate for an agent to decide usage.

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 is empty (0 parameters), so the baseline is 4. The description doesn't need to explain parameters, and it doesn't invent any. It implicitly confirms the tool takes no arguments.

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

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

The description uses the specific verb 'Get' and identifies the resource as 'the talent corpus' with concrete output details ('counts, top skills/locations'). This clearly distinguishes it from sibling tools like get_candidate or get_contact, which target individual 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?

The description clearly implies the tool is for corpus-level aggregate stats, not individual lookups. While it doesn't explicitly name alternatives or exclusions, the context signals (sibling tool names) make the use case obvious. A slight deduction for not stating 'when not to use' explicitly.

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 the description adds useful context about the document's scope (rate limits, privacy, etc.). It does not describe return format or size, but given annotations cover safety, 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 single sentence is front-loaded with the action and resource, then lists contents and usage scenarios. Every clause adds value; 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?

For a documentation tool with no parameters and no output schema, the description covers what it returns, why it exists, and when to call it. It is fully sufficient for an agent to select and invoke 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?

The tool has zero parameters, so the baseline is 4. The description adds no parameter info, which is fine because there are none to document.

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 the full QueryQuarry reference and lists its contents (how it works, tools, filters, tips, rate limits, privacy). It uses a specific verb ('Get') and resource, and is easily distinguished from sibling tools that perform specific data operations.

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

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

Provides explicit when-to-use scenarios: needing detail beyond tool descriptions, guiding new users, or before composing complex searches. However, it does not name specific alternative tools or state when not to use it, so it stops short of a 5.

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

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

The description adds behavioral context beyond the annotations by stating 'no duplicates' and characterizing the tool as a 'standing alert' for incremental updates. The readOnlyHint is consistent with the read-only nature of 'Get resumes', and no contradictions are 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 and front-loaded, with the core purpose in the first sentence, followed by usage guidance and a behavioral note. Every sentence contributes, with no redundant information.

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

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

For a tool with a single parameter and no output schema, the description covers the essential aspects: purpose, usage pattern, and distinct behavior. It references 'search_candidates' for filter details, which is sufficient given the constraint that only the 'since' parameter is exposed in this 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 schema only describes the 'since' parameter as 'ISO timestamp', but the description adds meaningful semantics by explaining it's the cutoff for 'new or updated' resumes and recommending 'yesterday's timestamp' for daily runs. This significantly helps an agent set the parameter correctly.

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 resumes that are new or updated since a timestamp, using the verb 'Get' and specifying the resource ('resumes'). It distinguishes itself from sibling tools like 'search_candidates' by mentioning 'same filters' but scoped to new/updated entries, and from 'get_candidate' which likely retrieves a single candidate.

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 operational guidance: 'Call daily with yesterday's timestamp' specifies when and how to use the tool. It also notes that the same filters as 'search_candidates' apply, which signals an alternative for broader searches, though it doesn't explicitly name when not to use this tool.

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

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

Annotations already declare readOnlyHint=true, so the description adds no additional behavioral context. It does not mention pagination, status filtering behavior, or what the response contains beyond 'candidates'. The description adds minimal value beyond the annotation.

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 front-loads the purpose. However, it is under-specified, lacking any elaboration on parameters or usage. It is efficient but not appropriately sized for the information needs.

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

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

Given the low complexity (2 optional params, no output schema) and good annotations, the description still fails to provide complete context. It does not explain how to use page/status, what results to expect, or how this relates to other tools. The description is too sparse for an agent to invoke correctly without further assumptions.

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 0%. The description does not explain the 'page' or 'status' parameters at all, leaving the agent without any clue about their purpose, allowed values, or how they affect results. No compensation for missing schema documentation.

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

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

The description clearly states the action ('Get') and the specific resource ('your saved candidates (watchlist)'), distinguishing it from sibling tools like get_new_candidates and search_candidates. The verb+resource structure is precise and unambiguous.

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

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

The description gives no explicit guidance on when to use this tool versus alternatives such as search_candidates or get_candidate. It implies usage for viewing watchlist, but does not state exclusions or mention the optional page/status parameters that affect usage.

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

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

Annotations already convey that the tool is non-read-only, non-destructive, and idempotent. The description adds that it's optional and used for marketplace measurement, but doesn't disclose further side effects or return behavior. No contradiction with annotations.

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

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

The description is extremely concise—two short sentences that front-load the action and include the outcome options. 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?

The description covers purpose and outcomes well, but the schema's required-field oddity (only 'outcome' required despite likely needing a contact reference) is not addressed. Also, no information about return values or post-report effects is given, leaving some gaps for a mutation 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 description explains the meaning of the 'outcome' parameter with its three enum values, but does not elaborate on 'code' or 'contact_id'. With 0% schema coverage, the description partially compensates for the main parameter but leaves the other two ambiguous.

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

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

The description clearly states the action with a specific verb ('report') and resource ('outcome on an accepted contact'), and enumerates the exact outcome values. It effectively distinguishes this tool from the read-only sibling tools like get_contact and search_candidates.

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 context on when to use it ('on an accepted contact') and why it's valued ('how the marketplace measures that consented outreach beats cold outreach'). It lacks explicit alternatives or when-not-to-use conditions, 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 only give hints (readOnly=false, openWorld=true, idempotent=false, destructive=false), so the description carries the full burden. It discloses the asynchronous notification flow, email delivery on acceptance, privacy protection, metering, and the one-active-offer rule. 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?

Dense but well-structured: the opening sentence states purpose, followed by workflow, side effects, and alternatives. Every sentence adds value—privacy, metering, prerequisites, and limits—with no fluff or repetition.

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

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

With no output schema, the description explains the asynchronous outcome (email with contact info and verification code) and directs status checks to get_contact. It covers prerequisites, limits, privacy, and the decision process, making the tool's behavior predictable 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 low (33%, only message), so the description must compensate. It clarifies that candidate_id refers to the single candidate being contacted and that resume_id comes from a prior get_candidate call. The message parameter is fully specified in the schema, providing adequate semantics for all parameters.

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

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

The description opens with a specific verb and object ('Reach out to one candidate') and clearly explains the request workflow. It distinguishes itself from sibling tools by noting get_contact shows status, making it clear this tool initiates the contact request rather than checking its status.

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

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

Provides explicit usage context: requires a prior get_candidate for this resume, metered (counts toward limit), one active offer per candidate, and respect declines. It also points to get_contact as the status-checking alternative, giving the agent clear guidance on when to use each 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 indicate readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds the watchlist destination and optional notes but does not elaborate on side effects like updating existing entries or whether notes override previously saved notes. This is consistent with annotations, adding minimal extra context.

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

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

The description is a single, front-loaded sentence with no unnecessary words. It communicates the core action and optional attribute efficiently.

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 save operation with no output schema, the description is mostly complete but lacks clarity on parameter semantics and potential behaviors like handling duplicate saves. It provides adequate high-level context but leaves gaps that the schema annotations do not fill.

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 0%, so the description must explain the parameters. It only identifies 'notes' as optional and implies candidate_id/resume_id identify a candidate resume. It does not clarify the distinction between candidate_id and resume_id, their format, or how notes are handled. This is insufficient given the low schema coverage.

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

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

The description uses a specific verb ('Save') and clearly identifies the resource ('candidate resume') and destination ('watchlist'), also mentioning optional notes. It fully distinguishes from sibling tools like get_watchlist and search_candidates by indicating a write action to the watchlist.

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

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

The description implies usage when one wants to add a candidate resume to a watchlist, but it does not explicitly state when to use this tool over alternatives or mention any exclusions. No comparison to sibling tools is provided, so it relies on the name and context.

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

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

The annotation readOnlyHint=true already indicates a safe read operation, but the description adds crucial behavioral context: results are anonymous, include no contact info, are paginated (max 25), and sorting is arithmetic over the user's criteria with recency as default. This goes well beyond the annotation and helps the agent set expectations.

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, tightly packed with high-value information: purpose, output contents, explicit exclusions, alternative tool, filters, sorting, and pagination. No filler or repetition; the most important facts are 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?

With 18 parameters and no output schema, the description compensates by specifying the shape of the anonymous match card (headline, skills_matched, seniority, location, availability, salary range, snippet) and the always-paginated behavior. It also provides enough context about filtering and sorting to use the tool effectively, and points to get_candidate for deeper data.

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

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

The schema already covers 72% of parameters with meaningful descriptions, so the description's high-level filter list adds limited new parameter semantics. It reinforces the filter categories and notes pagination/sorting defaults, but does not materially improve on the schema's detailed parameter explanations.

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

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

The description opens with a specific verb+resource ('Search the talent graph') and clearly defines the scope: returns anonymous match cards with listed fields but no PII. It explicitly distinguishes from sibling tools by directing to get_candidate for the deeper anonymous profile, and the mention of filtering/sorting differentiates it from other candidate 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 to call get_candidate for a 'metered reveal' of the deeper profile, providing an alternative tool and the context for when to use it. It also covers sorting defaults and pagination, giving the agent clear guidance on behavior without needing to infer.

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