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

With no annotations, the description carries the full behavioral burden and does disclose the critical trait: the application cannot be easily withdrawn. It also pins the confirmation string exactly. It does not cover auth prerequisites, duplicate-application behavior, or what happens on failure, which is a real gap for an irreversible mutation.

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 purpose is front-loaded in the first sentence, followed by the irreversibility warning and parameter constraints. Both paragraphs earn their place, with no filler.

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

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

For a three-param irreversible write tool with an output schema, the description covers the essentials an agent needs to call it safely. Missing are auth/login requirements and error or duplicate-handling behavior, which matter given the stated irreversibility.

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 compensates well: job_id and job_kind are constrained to fresh search results, job_kind must not be guessed, and confirmation must match a literal string. It stops short of enumerating valid job_kind values, which would fully close the gap.

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?

States a specific verb and resource ('向猎聘投递指定职位') with the scope made explicit. It is clearly distinguishable from siblings like liepin_search_jobs and liepin_get_resume by the write action alone, though the description does not name an alternative 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?

Explicit preconditions are given: first display the job details and get the user's explicit confirmation, and use job_id/job_kind only from this session's Liepin search results. It also states an explicit negative constraint — job_kind must not be guessed — so there is little left to infer.

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 usefully discloses that only raw JSON from the official Liepin CLI is returned and no copy is saved, but it does not state read-only side effects, auth requirements, rate limits, or error behavior.

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

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

Two short sentences with zero waste: the purpose is front-loaded, followed by the key behavioral constraint about raw JSON and no saved copy. 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?

For a zero-parameter read tool with an output schema, the description is nearly complete: it identifies the target resource, implies the authenticated account, and notes the raw JSON return with no persistence. The only minor gap is the absence of explicit read-only/safety language, which matters because no annotations are present.

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 does not need to add parameter meaning, and the empty schema is consistent with the no-parameter call.

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 names a specific verb ('读取') and resource ('简历') scoped to '当前猎聘账号', so an agent can tell this retrieves the authenticated user's resume. It does not explicitly differentiate from siblings, though the siblings (job search, expectation update, job apply) are unrelated 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?

Usage is implied by '当前猎聘账号简历' – the tool is for reading the current account's resume. There is no explicit when-to-use guidance, no statement of prerequisites, and no mention of alternatives or 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 exist, so the description carries the full burden. It does disclose two meaningful behaviors: page is 0-indexed and the return is raw CLI JSON with no assumed field structure. It does not mention auth requirements, rate limits, total result count, or how many items a page returns, which matters for a scraping-style search.

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?

Short and front-loaded: what the tool does first, then format caveats, then return behavior, then a precondition. No filler sentences. It could be slightly better organized by grouping the parameter-format notes together.

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?

Output schema exists, so return shape need not be described (and the 'raw JSON, don't assume fields' note is a helpful extra). But with 10 undescribed, enum-less, all-optional parameters, the description compensates only partially — an agent still lacks enough to fill salary and filter fields confidently.

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% and none of the 10 parameters (salary_floor, salary_cap, salary_kind, comp_nature, edu_level, work_experience, address, job_name, company_name, page) has a description or enum. The description only clarifies that filter values must be passed as raw CLI-format strings and that page is 0-based; it never explains the expected format or accepted values for salary/edu/experience filters, leaving the agent to guess.

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?

States a specific verb and resource ("搜索职位" / search jobs) and names the channel (Liepin official CLI). Siblings (get_resume, apply_job, update_job_expectation) are clearly different operations, so differentiation is implicit rather than argued. It could not be confused with anything else in the toolset.

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?

"调用前应确认目标城市、岗位和薪资条件已明确" gives a pre-call checklist, which is useful implied usage guidance. However, it never says when this tool is the right choice versus not calling it at all (e.g. no results / different query strategy), and no alternatives are named. Guidance is present but thin.

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 must carry the behavioral burden, and it does disclose that this is a write operation requiring explicit user confirmation after viewing fields. It also constrains the confirmation string and record_id origin, though it does not describe reversibility, permission requirements, or how omitted optional fields affect existing data.

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 short and front-loaded: purpose first, then the mandatory confirmation workflow, then exact constraints and supported fields. Every sentence contributes necessary operational or safety 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?

The tool has 10 parameters, no annotations, and low schema description coverage, so the description should compensate more fully. It covers purpose, confirmation, record_id provenance, and field names, but not enough about field meanings or partial-update behavior; the output schema exists, so return values need not be explained.

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 parameter meaning depends entirely on the description. The description lists all supported field names and adds important semantics for confirmation and record_id, but leaves several fields such as dq, salary units, workweek semantics, and allowed workType values unexplained.

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 a specific verb and resource: '更新猎聘的求职期望' (update Liepin job expectation). This is unambiguous and clearly distinct from the sibling tools, which search jobs, fetch resumes, or apply to jobs.

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

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

It explicitly requires the user to view the updated fields and give clear confirmation before the write operation, and states the exact confirmation string and valid source of record_id. Usage context is strong, though there is no explicit statement of when not to use the tool or an alternative path.

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