Skip to main content
Glama
Ploid MCP

Ploid MCP

Official
by ploidcom

Research a person

research_person

Start source-reviewed research on a person using a person ID or LinkedIn profile URL, with optional goal, website, and anchor links; receive a resumable run ID for status tracking.

Instructions

Start source-reviewed research on one person, identified by exactly one of person_id (selected from search_people) or linkedin_url (an explicit HTTPS LinkedIn person profile URL); never pass both. For a name, search and ask the user to choose first. Set type to standard for lighter research (10 ACU) or leave the default deep (25 ACU); moving a standard profile up to deep costs the 15 ACU difference. Optionally pass goal (what to look for), website_url (their own site) and up to 10 anchors (public URLs you know belong to them, such as an X profile or a podcast episode); a run with these is not served from or saved to the shared profile. First workspace access is charged even for an already-cached profile; rereads at the same or a lower level within 90 days are free. Not-found and uncertain results are free. Returns a resumable run_id when pending; use get_research_status for the result.

Input Schema

NameRequiredDescriptionDefault
goalNoWhat to look for, up to 2000 characters.
typeNostandard (10 ACU) or deep (25 ACU, the default).
anchorsNo1 to 10 public HTTPS URLs you know belong to this person, such as an X profile or a podcast episode.
person_idNoA person_id returned by search_people, up to 500 characters. Provide this or linkedin_url, not both.
website_urlNoThe person's own website, an HTTPS URL up to 2000 characters.
linkedin_urlNoAn HTTPS LinkedIn person profile URL such as https://www.linkedin.com/in/name, up to 2048 characters. Provide this or person_id, not both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true; the description goes far beyond that with ACU pricing per type, the discount for upgrading standard to deep, charging on first workspace access even when cached, free rereads within 90 days, and free not-found/uncertain results. It also discloses that a run may return a pending run_id rather than the final result.

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

Conciseness4/5

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

The identity requirement is front-loaded and nearly every clause carries decision-relevant information (pricing, caching, alternatives). It is dense and semicolon-chained, so an agent must parse carefully, but there is little filler to cut.

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

Completeness5/5

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

For an asynchronous, paid, open-world research trigger with no output schema, the description covers inputs, cost, caching exceptions, free outcomes, and how to retrieve results via a resumable run_id. Nothing an agent needs to invoke it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is a 3, but the description adds real meaning: the exclusive-or constraint on person_id/linkedin_url, the cost implications of the type enum, and what anchors should be (public URLs known to belong to the person, like an X profile or podcast episode). Remaining gaps are minor, e.g. goal is only loosely described as 'what to look for'.

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

Purpose5/5

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

States a specific verb and resource ('Start source-reviewed research on one person') and immediately narrows the identity input to exactly one of person_id or linkedin_url. It is clearly distinguishable from search_people (used for name lookup) and get_research_status (used for results).

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

Usage Guidelines5/5

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

Gives explicit routing rules: for a name, search and ask the user to choose first; never pass both identifiers; use get_research_status to retrieve results. It also states when the run is not served from or saved to the shared profile, which changes tool choice behavior.

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