按人物姓名、人物类型、地区、当前公司、当前投资机构、教育经历或过往工作经历搜索人物画像，返回对外可见人物的当前任职、教育经历和过往工作经历等字段。
| Name | Required | Description | Default |
|---|---|---|---|
| cities | No | ||
| cursor | No | ||
| fields | No | ||
| keyword | No | ||
| location | No | ||
| is_on_job | No | ||
| page_size | No | ||
| provinces | No | ||
| ever_job_keyword | No | ||
| education_keyword | No | ||
| person_type_keyword | No | ||
| current_company_keyword | No | ||
| current_investor_keyword | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that only externally visible people are returned and that current role, education, and work history fields are included, which is useful behavioral context. However, there are no annotations, and it does not mention pagination, result thresholds, filtering behavior, or other operational 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?
One compact sentence front-loads the core purpose and then lists criteria and return fields.N Oc extra filler sentences. The list of criteria is long but necessary given the tool's complexity.
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 13-parameter search tool with no schema descriptions and no annotations, this single sentence is under-specified:it covers main int aims but leaves pagination, parameter relations, requiredness, and edge-case behavior to inference. Output flexible exists, so return-format omission is less harmful.
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 for 13 undocumented parameters. It lists semantic search dimensions that map roughly to keyword parameters, but it never names specific parameters such as keyword, person_type_keyword, education_keyword, is_on_time, or future. Parameters like cursor, page_size, and fields are completely unaddressed.
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 action ('搜索人物画像') and enumerates the searchable dimensions (name, person type, region, company, investment institution, education, work history). It clearly identifies the resource and purpose, though it does not distinguish it from siblings like search_investors or get_person_profile.
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 this tool is for searching person profiles by broad criteria, but it gives no explicit guidance on when to use it instead of search_investors, get_person_profile, or other sibling tools. No exclusions, prerequisites, or alternative-routing hints are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource and action: counting vs searching vs retrieving profiles vs ranking vs resolving. There is no ambiguity as tools like count_companies and search_companies have clearly separated purposes (count vs list). Even similar tools like search_companies and search_closed_companies are distinguished by company status.
All tool names follow the verb_noun pattern (e.g., search_companies, get_company_profile, resolve_companies) using snake_case consistently. The naming is predictable and clear, with only minor variations like aggregate_funding_by_tags which still starts with a verb.
With 17 tools, the server covers a comprehensive set of operations for a company/funding database without being overwhelming. Each tool serves a specific need, and the count aligns well with the domain's complexity.
The tool set covers all major operations for querying companies, funding, investors, events, FA cases, tags, and lookups. It includes both aggregated counts and detailed listings, ranking, and name resolution. No obvious gaps for a read-only data retrieval server.
