tpool 招聘数据 MCP

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It usefully states 免 key (no API key required) and implies a read-only enumeration with counts, but does not explicitly confirm read-only status, rate limits, or response shape beyond 'and their respective counts'.

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?

One compact sentence plus a three-character tag. Every clause earns its place: purpose, output content, usage context, and auth exemption. Front-loaded and free of 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 zero-parameter, no-output-schema enumeration tool, the description covers what it does, why to call it first, and that it returns filters with counts, plus auth. No significant missing element for correct invocation, though a note on exact response shape could help.

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 (baseline 4). The description gives recruit_type as an example of the enumerable filters, which helps an agent understand what the returned filter keys will look like, but there are no input parameters 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?

States a specific verb (枚举) and resource (公告的可选筛选项), including filter examples and counts. The phrase 供先查后搜 implicitly distinguishes it from the search sibling, though it never names tpool_search_announcements. Clear and specific overall.

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

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

Explicitly frames the tool as a pre-search step (先查后搜), giving a clear context for when to call it. It does not name alternatives or state when not to use it, but the routing intent is unambiguous.

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 the burden and does add behavioral context: the return is markdown raw text and no key is required (免 key), telling the agent this is an open, read-only content fetch. It omits caching/volatility and any size or freshness caveats, but for a zero-parameter read-only document fetch that is minor.

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, then the output format, then the must-read guidance and the auth note. Every clause carries information; 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 parameterless, annotation-free, no-output-schema tool, the description covers what it returns (markdown), why to call it (pre-integration reading) and the auth posture (no key). Only marginal items such as document stability or language locale are unaddressed.

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 there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. No misleading parameter hints are present.

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 resource (tpool platform code of conduct) and the delivered form (markdown raw text), which is clearly distinguishable from the sibling search/quota/job tools. It does not explicitly contrast itself with any sibling, but the verb+resource pairing is 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?

"接入前必读" gives an explicit condition for when to call it (before onboarding/integration), which is more than implied usage. It stops short of naming alternatives or when-not-to-call, so it falls just under full 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses one important trait — '需 API Key' (requires an API key) — and implies a read-only fetch via '取', but says nothing about rate limits, error behavior, or output shape beyond the field list.

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 tightly scoped sentences; the operation and its returned contents come first, the parameter provenance second, and the auth note third. 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 one-parameter getter with no output schema and no annotations, the description covers the essentials: what is fetched, what fields come back (compensating for the absent output schema), where the id originates, and the auth requirement. Only behavioral edge cases (errors, limits) are left unaddressed.

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 compensate, and it does: it explains that job_id is the integer id returned as items[].job_id from tpool_search_jobs. That provenance meaningfully exceeds the bare 'Job Id' property name in the schema.

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

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

States a specific verb+resource — '取单个岗位详情' (fetch a single job's details) — and enumerates the returned fields (JD body, education/experience/skill requirements, salary, source link). The scope word '单个' (single) cleanly separates it from the batch/list sibling tpool_search_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 establishes the workflow by stating job_id comes from tpool_search_jobs' items[].job_id, which tells the agent when this tool is the right follow-up call. It does not, however, spell out any when-not conditions or explicit alternatives beyond that provenance chain.

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 the full behavioral burden, and it discloses the key operational fact an agent needs: 'no key required' (免 key), implying an unauthenticated, side-effect-free read. For a zero-argument read-only meta call the remaining behavioral surface is minimal, so 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?

Two compact sentences: the first front-loads what the tool returns, the second front-loads how to use it. No filler, no repetition of the name.

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-param, no-output-schema tool, the description must itself convey the return content, and it does (statistics, stance, tips, skill list) plus the auth requirement and recommended call ordering. Nothing an agent needs to invoke it correctly is absent.

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 is no parameter to describe and the empty schema is self-consistent; nothing is added or missing.

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 resource (platform overview) and enumerates exactly what it returns: real-time statistics, platform stance/usage tips, and a skill-package list. An agent can tell this is a meta/introspection tool distinct from the search siblings, though it does not explicitly draw the boundary against tpool_code_of_conduct or tpool_my_quota.

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 states a concrete usage rule: 'after connecting, recommended first call, understand what the platform has, then decide how to search.' This clearly tells the agent when to invoke it (before searching). It stops short of stating exclusions or naming an alternative to use instead.

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

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

No annotations, so the description carries the burden. It discloses the auth requirement ('需 API Key') and that data is real-time remaining quota. It does not explain rate-limit behavior of this call itself or output format details, but for a zero-param read-only diagnostic, the auth requirement and the framing are meaningful additional 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?

Two short lines: first states what/it returns and the auth need, second is the actionable trigger. Front-loaded and waste-free, though the phrasing is terse to the point of near-cryptic for non-Chinese readers.

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?

A zero-param, no-output-schema diagnostic tool: the description tells the agent what it returns (identity + 8 quota dimensions with limit/used/remaining) and when to call it. Sufficient for correct invocation; only the absence of any response shape detail keeps it from a 5.

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?

Zero parameters, so baseline is 4. The description correctly implies no input is needed beyond the key — nothing to get wrong.

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 ('查询') and resource ('当前 key 的身份与 8 项功能配额实时剩余'), and specifies the exact data returned (limit/used/remaining). This clearly distinguishes it from the sibling tools, which are all about announcements/jobs/meta — none of which deal with quota.

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 when-to-use guidance: '被限流/超额时先调它自查' tells the agent precisely the trigger condition and even warns against the wrong action ('别盲目重试'). Names the situation that selects 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?

No annotations are provided, so the description carries the full burden. It discloses useful traits — no API key required and a daily-refreshed source — but says nothing about rate limits, pagination limits, or result ordering behavior beyond the sort parameter definition.

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 sentence is front-loaded, followed by a clean Args block with one line per parameter. Every line carries information; no padding 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?

For a six-parameter, no-annotation, no-output-schema search tool, the definition covers purpose, prerequisites, and all parameters well. The main remaining gap is the shape of the response (result fields, page/metadata), which is not described anywhere.

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 compensate, and it largely does: it documents all six parameters with examples (「国家电网」,「银行」,「秋招」), defaults (page 1, page_size 15), the sort enum values (deadline/created_at/popularity), and points to the filters tool for recruit_type values. It does not clarify that all parameters are optional.

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 (搜索/搜索校招·国央企招聘公告) and adds scope details: source coverage (国企肩标平台等), daily updates, and no-key access. It implicitly separates itself from tpool_search_jobs by naming the resource as announcements, but never explicitly distinguishes the two.

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 clear context (no key required, daily-updated source) and routes the agent to a sibling for a needed prerequisite: recruit_type values must be fetched via tpool_announcement_filters first. It offers no explicit when-not-to-use guidance versus tpool_search_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?

With no annotations, the description carries full burden and adds useful behavioral facts: it requires an API Key, returns in 'seconds' via pure SQL, and notes that Chinese URL encoding is handled at the MCP layer. It does not disclose read-only status explicitly or return/pagination format, but the added auth and encoding details are valuable.

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?

Front-loads the core purpose in one line, then lists parameters compactly. Every sentence adds information—examples, defaults, encoding note—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?

Given 5 parameters, no annotations, and no output schema, the description covers invocation fully (auth, all parameters, encoding) but does not describe what the search returns (e.g., job fields, pagination total). That missing return-shape context keeps it from a 5.

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 compensate fully. It documents all five parameters with examples, defaults (page_size default 20, max 50; page starts at 1), and semantic cues (city blank = nationwide, category leave blank if unsure). This goes well beyond the schema's bare types and defaults.

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 pair: keyword search of active job postings (在招岗位). Clearly distinguishes from siblings like tpool_get_job (single job retrieval) and tpool_search_announcements (announcement search) by naming the resource as job postings and the method as keyword 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?

Provides implicit usage context (keyword required, city blank means nationwide, category can be left blank if unsure), but never explicitly states when to choose this tool over tpool_get_job or tpool_search_announcements, nor any when-not conditions.

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