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

No annotations are provided, so the description must carry the burden. It discloses the tool returns a list of applications with specific fields, and warns that candidate_id differs from applicationId. However, it does not explicitly state that the operation is read-only, mention permissions, or report potential 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?

The description is structured into clear sections: purpose, API reference, parameter, and return fields. It is slightly verbose with the API endpoint reference, but overall 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 the output schema exists, the description need not detail return values, but it does so anyway. It covers purpose, parameter, return fields, and API mapping. Missing error handling or permissions, but adequate for a simple 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 0%, so the description adds significant value. It explains the parameter candidate_id meaning (candidate ID, not applicationId) and how to pass it (in body). This compensates fully for the lack of 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 tool queries all application records and statuses for a candidate, emphasizing that one person can apply for multiple positions. This distinguishes it from sibling tools like get_candidate_detail which returns a single candidate's info.

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 by stating 'one person can apply for multiple positions' and provides the corresponding API endpoint, but it does not explicitly state when to use this tool over siblings or provide exclusions.

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 mentions the API method (GET) implying read-only, notes return content structure, and warns that attachment/avatar URLs expire in 1 hour. This provides useful behavioral context, though explicit safety hints are missing.

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 with a clear first sentence stating purpose, followed by API reference, parameter description, return summary, and a key behavioral note. 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?

Given the complexity (single parameter, output schema exists), the description covers the essential aspects: purpose, parameter format, return contents, and URL expiration. Missing explicit permission or error information, but overall sufficient for a simple retrieval 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 has 0% description coverage, so the description fully compensates. It explains application_id as '候选人申请 ID' (candidate application ID) and importantly notes support for comma-separated multiple IDs with an example, adding significant meaning beyond the bare 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 states '获取单个候选人的完整信息' (get complete info of a single candidate), which is clear. However, it later allows comma-separated multiple IDs, creating slight ambiguity about single vs. multiple. It does not explicitly differentiate from siblings like search_candidates or get_candidate_applications.

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. It does not mention siblings or provide when-not-to-use conditions. The only context is the API endpoint, which is technical but not decision-guiding.

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?

Without annotations, the description carries the transparency burden. It explains the internal reuse of another endpoint and clarifies the data source (stageName from candidate detail). It implies read-only behavior but does not explicitly state idempotence. The implementation insight is helpful.

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

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

The description is concise with two sentences and a parameter bullet. It front-loads the purpose but includes implementation details that, while useful, extend beyond the core purpose. Still efficient overall.

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 an output schema, the description need not detail return values. It covers the parameter, implementation rationale, and data source. It is complete enough for an agent to use correctly, though lacks error handling or edge-case 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 0%, but the description explicitly documents the parameter: 'application_id：候选人申请 ID。'. This adds meaning beyond the schema's type-only definition, compensating for the lack of 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's purpose: '查询候选人当前所处的招聘阶段' (query the candidate's current recruitment stage). It distinguishes from siblings like list_stages (lists all stages) and get_candidate_applications (lists applications) by specifying it returns the stage for a specific application.

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

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

The description implies usage for querying a candidate's stage but does not provide explicit when-to-use or when-not-to-use guidance. It mentions the implementation limitation but lacks direct comparison to siblings or conditions for 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, so the description carries full burden. It discloses the underlying API call (GET /jobs) which implies a read operation and provides context about Moka's API limitations. It does not cover rate limits or authentication, but the behavioral information 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 structured with a purpose sentence, an implementation note, and parameter list. It is front-loaded and every part adds value, though it could be slightly more concise. 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 the presence of an output schema, the description adequately covers what the tool does, its parameters, and the unconventional implementation. It is complete for an agent to understand and invoke the tool, though it omits potential limitations or return format hints.

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 0%, so description must compensate. It explains job_id (job ID) and org_id (organization identifier, defaults to env variable if empty), adding meaning beyond the schema. It also explains the internal mechanism (extraction from GET /jobs).

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 '获取某职位的自定义字段' (get custom fields of a job), with a specific verb and resource. It distinguishes from sibling tools like get_job_detail (full job detail) and get_offer_custom_fields (different resource).

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 the implementation reason (no stable independent API) and that it extracts from GET /jobs, implying when to use this tool. However, it does not explicitly state when not to use it or provide specific alternatives, though siblings are listed.

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 mentions it fetches details but does not disclose whether it is read-only, authorization requirements, rate limits, or error behavior (e.g., if job not found). This is insufficient for a complete behavioral understanding.

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

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

The description is concise, consisting of a main sentence and a bulleted parameter list. It is front-loaded with the purpose and includes relevant API details. However, it could be slightly more structured (e.g., separating usage notes).

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 an output schema present, the description does not need to explain return values. It covers parameters well but lacks usage guidelines and behavioral transparency. For a simple retrieval tool, this is adequate but has clear gaps.

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

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

Schema description coverage is 0%, so the description compensates by explaining the purpose of each parameter: job_id is the job ID, org_id is the org identifier with a default from .env. This adds meaningful context beyond the schema's type 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 explicitly states it retrieves a single job's details including custom fields and recruitment process info, which clearly distinguishes it from siblings like list_jobs or search_candidates. The API endpoint is also provided for reference.

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 does not provide explicit guidance on when to use this tool versus alternatives. It implies usage for getting full details of a specific job, but lacks exclusions or context for choosing it over other tools like get_job_custom_fields.

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 fully carries behavioral disclosure. Reveals API endpoint, crucial return structure (social/campus keys, not generic data), implying read-only nature.

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?

3 clear sentences, front-loaded with purpose and API reference, no wasted text.

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?

Comprehensive given 0 params and output schema existing: covers purpose, API, and exact response format.

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 100% (0 parameters), baseline 3. Description does not need to add param info but adds value via return structure explanation, though not about 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?

Clear verb 'get' and specific resource 'offer custom fields', distinct from siblings which deal with candidates, jobs, departments, etc. Includes context for social/campus recruitment.

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 when-not-to-use, but the tool is unique so usage is implied. Lacks guidance on prerequisites 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?

The description discloses one important behavioral trait: the response uses a non-standard structure ('{"departments": [...]}' instead of the typical 'data' field). However, with no annotations, it does not explicitly state read-only nature, authentication requirements, or potential side effects. This partial disclosure provides some transparency but leaves gaps.

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 composed of three concise sentences, each serving a clear purpose: stating the function, providing the API reference, and noting the return structure caveat. It is front-loaded with the primary purpose and contains no redundant or 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's simplicity (no parameters) and the existence of an output schema, the description adds valuable context about the non-standard return format. It could further explain the tree hierarchy or pagination, but for a basic list tool, it covers the essential points. The output schema presumably handles remaining details.

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

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

The input schema has zero parameters, so the description correctly has no parameter documentation. Per the guidelines, 0 parameters yields a baseline of 4. The description does not need to add anything beyond what the empty 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 explicitly states '查询部门列表（树形组织架构）' which translates to 'query department list (tree organizational structure)'. This clearly identifies the tool's purpose of listing departments in a hierarchical tree format. The inclusion of the specific API endpoint (GET /departments v1) further solidifies its function, leaving no ambiguity.

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?

While the description accurately describes what the tool does, it lacks explicit guidance on when or when not to use it. There are no sibling department tools, so alternatives are absent, but no prerequisites or context for usage are provided. The agent must infer usage from the tool's name and purpose, which is adequate but not proactive.

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 important behavioral details: closed jobs not unchecked 'cancel display on website' are still returned, and deleted jobs are not. This adds context beyond the schema. No annotations provided, so description carries full burden.

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?

Concise and well-structured with bullet points for parameters and behavioral notes. It includes the API endpoint for reference without unnecessary fluff. Could be slightly more streamlined.

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 all necessary context: required parameter, optional parameters with defaults, and edge case behaviors. With an output schema existing, it appropriately omits return value details.

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

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

Despite 0% schema description coverage, the description explains each parameter clearly: mode is required with enum values, org_id defaults to environment variable, limit sets max results. This adds significant value over 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?

Clearly states '查询职位列表' (query job list) and specifies the Moka API endpoint. It distinguishes from sibling tools like get_job_detail and list_departments by its focus on listing jobs with specific filters.

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 parameter details and behaviors for edge cases, but lacks explicit guidance on when to use this tool versus alternatives like search_candidates or get_job_detail. The description assumes the user knows to use it for listing jobs.

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. The description implies a read-only operation via GET, but does not explicitly confirm safety, permissions, or other behavioral traits. 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?

Very concise, three sentences: purpose, API reference, and return fields. No unnecessary words, 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 parameters and presence of an output schema, the description is complete. It lists key return fields and API version, sufficient for a simple list 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?

No parameters in the input schema (0 params), so the description does not need to add parameter details. Baseline 4 applies as per rules.

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 pipelines and mentions the fields returned. It does not explicitly distinguish from sibling tools like list_stages, but the resource is distinct enough.

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 or not use this tool versus alternatives. The description simply states what it does without contextual advice.

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 must carry the full burden. It does not disclose any behavioral traits beyond returning id, name, type. There is no mention of pagination, sorting, ordering, or potential performance implications. For a list operation, this is a significant gap.

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: four lines with no extraneous information. It front-loads the purpose, then lists parameters and return fields. Every sentence adds value.

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

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

Given the simplicity of the tool (list stages with one optional filter) and the presence of an output schema, the description is minimally adequate. However, it lacks details on pagination, ordering, or whether all stages are returned. For a complete picture, an agent might need 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?

The schema has 0% description coverage, so the description must compensate. It clearly explains pipeline_id as '可选，按指定流程过滤阶段' (optional, filter by specified pipeline), adding meaning beyond the schema's type and default. The return fields are also listed, though that is not parameter 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?

The description clearly states it lists stage information, using the verb '获取' (get/list) and resource '招聘阶段' (recruitment stages). It specifies the API endpoint and return fields. However, it does not explicitly differentiate from sibling tools like get_candidate_stage or list_pipelines, though the context makes it fairly clear.

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

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

The description mentions an optional pipeline_id filter but provides no guidance on when to use this tool versus alternatives like get_candidate_stage (which gets a candidate's stage) or list_pipelines. There is no explicit 'when to use' or 'when not to use' advice.

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, and the description does not disclose any behavioral traits beyond the basic query operation. It lacks information on pagination, permissions, rate limits, or side effects, which is needed since annotations are absent.

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 a clear purpose statement, an API endpoint reference, and a structured parameter list. Every sentence adds value, and the most important 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 the parameter count and presence of an output schema, the description covers the core functionality and parameter details. However, it lacks context on pagination or result structure, though the output schema exists to supplement. Overall, 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 0%, so the description bears full responsibility. It adds significant value by providing examples and clarifying that all parameters are required, which the schema (with only titles) does not convey. Each parameter is explained with format and 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 that the tool queries candidates under a specified talent pool with archive time range filtering. It uses specific verbs and resources, distinguishing it from siblings like list_talent_pools (lists pools, not candidates) and search_candidates (general 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?

The description implies usage by listing required parameters and giving examples, but does not explicitly state when to use this tool versus alternatives like search_candidates or list_talent_pools. No exclusions or context 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?

No annotations are provided. The description only mentions it returns an array of talent pools with specific fields, but does not disclose any behavioral traits such as read-only nature, authentication needs, rate limits, or potential 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?

The description is two sentences, front-loaded with the purpose, and contains no extraneous content.

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

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

Given no parameters and an existing output schema, the description adequately covers the tool's purpose and basic return structure. No further details are necessary.

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?

There are zero parameters, so schema description coverage is 100%. The description adds no parameter info, which is acceptable as none exist.

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 talent pools, provides the Moka API endpoint, and lists returned fields (id, name, hireMode, isPrivate). It is specific and 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?

No guidance on when to use this tool versus alternatives. No prerequisites, exclusions, or context 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?

With no annotations, the description carries full behavioral disclosure. It reveals how the tool handles Moka's 500 error by returning an empty result, supports cumulative pagination via limit, and requires a positioning condition. This provides useful context beyond a simple read operation, though authentication and rate limits are not mentioned.

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 heading, bullet points for parameters, and a note section. It front-loads the core purpose. The reference to the Moka API endpoint adds a bit of redundancy, but overall it is efficient and each part 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 annotations and 0% schema coverage, the description is thorough: it explains all seven parameters, error handling, pagination, and a usage condition. Since an output schema exists, return values need not be described. It could add more about typical scenarios or best practices, but it is sufficiently complete for an AI agent.

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

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

Schema description coverage is 0%, so the description compensates well by explaining each parameter's meaning (e.g., stage enum values, exact search for email/phone, time range, order, limit with pagination). It also notes the need for at least one condition (stage or applicationId). However, applicationId is not actually a parameter in the schema, which weakens the explanation.

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

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

The description clearly states it searches candidates by criteria and references the Moka API endpoint. It lists specific parameters, making the purpose evident. However, it does not explicitly differentiate from sibling tools like get_candidate_applications or get_candidate_detail, though the distinction is implicit by its search nature.

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

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

The description provides parameter notes and an important usage condition (need at least one of stage or applicationId), but applicationId is not present in the input schema, causing confusion. No explicit guidance on when to use this tool over alternatives or when not to use it is given.

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