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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds real behavioral context the annotations don't: that keyword does full-text matching including job body text (104 連內文比對), which affects result volume. It says nothing about the `full` flag's behavioral effect.

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 compact line that front-loads the resource and then attaches parameter semantics with semicolons. No filler; the only cost is that the terse phrasing borders on cryptic.

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 4-parameter tool with no output schema and no parameter descriptions in the schema, the description leaves the `full` flag completely undefined and gives no indication of what the company profile response contains. An agent would have to guess at one parameter and cannot predict the return shape.

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 carry the full parameter burden. It explains with_openings and keyword reasonably well, but `full` — one of four parameters — is never mentioned in either the schema or the description, leaving its effect entirely unknown.

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?

"公司簡介" identifies the resource (company profile) but is a bare noun phrase with no verb, and it never states how this differs from get_job or search_jobs. The secondary clauses about openings hint at the capability but the core purpose statement is vague.

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 gives conditional guidance for two optional parameters (when to set with_openings, when to use keyword), which is more than nothing. But there is no statement of when to call this tool instead of the sibling job-search tools, and no explicit "don't use for X" 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?

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add semantics — and it does: it discloses that applicants data is scoped to the last two weeks and includes applicant background, and that both extra flags are restricted to 104-sourced data. It still omits what happens if a flag is requested on a non-104 job (error vs empty).

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 dense clauses, zero filler, with the primary purpose and the full-text flag front-loaded. The telegraphic style (＝, abbreviations) is efficient but slightly terse for non-Chinese-reading agents.

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 must frame the return payload; '職缺完整內容' gives a rough idea, but there is no indication of structure or size difference between full=True and default. The required job_id and the failure mode for restricted flags are the notable gaps for a four-parameter read 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 0%, so the description must carry parameter meaning. It defines three of the four booleans (full, applicants, similar) with concrete semantics, including a time window for applicants, but says nothing about job_id — the one required parameter — such as its format or that it comes from search_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?

States a specific verb+resource: retrieving the complete content of a job posting (職缺完整內容), and immediately clarifies the 'full' variant. It is implicitly distinguishable from search_jobs, but never names or contrasts any sibling, so it stops short of a 5.

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?

Says when to flip 'full' (full=True 看全文) and flags a hard constraint that applicants/similar only work on 104 data. However there is no guidance on when to use the applicants or similar flags versus calling search_jobs or get_company instead, leaving routing to inference.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds the traversal behavior (empty name returns children of parent), which is genuine context beyond the annotations, but says nothing about output shape or result limits.

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, front-loaded sentences with zero filler; the primary purpose is stated first and the parameter behavior second. Nothing is redundant.

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 3-parameter lookup with no output schema and 0% schema coverage, the description covers the parameter interplay but does not document the full set of valid kind values or what a returned code list looks like. Adequate but with visible gaps given the complete absence of structured parameter documentation.

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 carry the load, and it does reasonably well: it implies kind takes 'area' or 'jobcat', and it explains the interaction between name and parent (empty name = list next level; empty parent = top level). It omits the default values and exact accepted kind strings, keeping it from a 5.

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 pairs a specific verb (查/look up) with a specific resource (地區 area codes, 職類 jobcat codes), so an agent understands this is a reference-code lookup tool. It does not, however, differentiate itself from siblings like search_jobs or get_job, so it stops short of a 5.

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 second sentence gives implied usage: empty name lists the next level under parent, and empty parent means top level. That tells the agent how to invoke it for hierarchy traversal, but there is no explicit when-to-use guidance or comparison against the sibling lookup/search 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 cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower. The description adds two genuinely useful behavioral facts beyond annotations: the pages 1~5 window and the caveat that these are sample statistics, not the whole site (非全站), which materially affects how results should be interpreted.

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 compact clauses: what it returns, where to find parameter docs, and the sampling caveat. Front-loaded with the resource and scope, 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 read-only aggregate tool with no output schema, the description does state the returned statistics (count/min/quartile/median/max) and the sample-vs-full-site limitation, which is solid. But with 9 undocumented parameters and only a pointer to a sibling tool, an agent cannot confidently supply filter arguments.

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% across 9 parameters, so the description must carry the burden. It clarifies only the pages range (1~5) and otherwise defers with '參數同 search_jobs', leaving area, jobcat, keyword, job_type, my_years, new_only, education and remote_only entirely undocumented in either schema or description, and requiring cross-tool inference.

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+resource: it fetches the first pages of job listings that publish salary and computes per-unit statistics (count, min, quartile, median, max). This clearly distinguishes it from search_jobs (raw listings) and get_job (single posting). It is not quite a 5 because the '依單位' grouping key is left implicit.

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 use case (aggregate salary stats rather than raw job results) and notes '參數同 search_jobs', routing the agent to that sibling for parameter knowledge. However it never states explicitly when to prefer this over search_jobs or any when-not condition.

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 cover read-only/idempotent/open-world, and the description adds critical non-obvious behavior: filters other than keyword/area are silently dropped for non-104 sources, 104 excludes 面議 postings unless include_negotiable=True, and per_page is capped at 30 with page-based pagination. These are traps an agent would otherwise fall into.

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?

Purpose and return shape are front-loaded in the first line, and every subsequent line adds concrete constraint information with no filler. The one drawback is density: parameter rules are packed into a continuous stream without line-level labels, which slows scanning for a 16-parameter tool.

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 16-param tool with no output schema and zero schema descriptions, the description covers the highest-risk areas (source-specific filter support, salary unit, experience matching, pagination) and states the return is a table. It falls short by leaving job_type, new_only, education, and sort partially or wholly unexplained.

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 carries the full burden; it explains keyword/keyword_en interplay, Chinese-name conventions for area/jobcat, the salary_min↔salary_unit coupling, include_negotiable, my_years, and pagination limits. However job_type, new_only, education, and the full semantics of the sort enum are never mentioned, leaving four parameters undocumented anywhere.

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 ('搜尋職缺，回傳表格') and immediately clarifies the return shape plus downstream routing (id → get_job, company_id → get_company). It distinguishes itself from the detail-fetching siblings but never clarifies its relationship to salary_overview or sources, so sibling differentiation is incomplete.

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?

Gives explicit routing rules: keyword is Chinese for 104, keyword_en is English for other sources, and when only one is supplied both are shared. It also documents which filters are honored per source (yourator → sort=newest, boards → remote_only) and that unsupported conditions are not silently applied, which is exactly the when-to-use/when-not-to-use guidance an agent 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint, so the safety and network-dependence profile is covered. The description adds value by naming the specific external boards probed and implying a reachable/blocked result shape, but it says nothing about timing, rate limits, or caching 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?

A single sentence with no filler that front-loads the action (即時檢查) and then the resources inspected. Every clause carries 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 parameterless probe with no output schema, the description conveys what is examined and the binary outcome (reachable vs. blocked). It leaves the exact result format unspecified, but that is a minor gap for a tool this simple.

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 takes zero parameters, so the baseline is 4. There are no parameters whose meaning the description would need to clarify.

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 concrete verb (即時檢查 / check in real time) and a concrete resource (reachability of 104, Yourator, and foreign job boards). It is unambiguous what the tool does despite the vague tool name 'sources'. It does not, however, explicitly distinguish itself from siblings like search_jobs, which is why it falls short of a 5.

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?

There is no explicit when-to-use guidance, no prerequisites, and no mention of alternatives. An agent can infer this is a health/probe check to run before searching, but nothing in the text states that or excludes any scenario.

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