Skip to main content
Glama
Ploid MCP

Ploid MCP

Official
by ploidcom

Get a person's phone number

get_phone

Look up a person's mobile phone number by person_id or LinkedIn URL; unresearched people start standard research and return a run_id for the result.

Instructions

Look up one person's mobile phone number, identified by exactly one of person_id (from search_people) or linkedin_url: 10 ACU when found, free when not. Never upgrades an existing profile: a person researched at any level is reread for free. An unresearched person starts standard research_person (10 ACU on success; deep later costs the 15 ACU difference) and returns a run_id; the phone then arrives with the completed get_research_status result, so do not call get_phone again for it.

Input Schema

NameRequiredDescriptionDefault
person_idNoA person_id returned by search_people, up to 500 characters. Provide this or linkedin_url, not both.
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

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description supplies the economics (10 ACU when found, free when not), the no-upgrade rule (a previously researched profile is reread free), and the side effect that an unresearched person triggers a billed research run with a deep-upgrade delta of 15 ACU. The indirect return path via get_research_status is disclosed, which is exactly the non-schema behavior an agent needs.

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?

Front-loaded with the action and identifier constraint, then the cost and side-effect rules; every clause carries information. It is dense and the final clause about the run_id path is long, but nothing is redundant.

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 a two-parameter lookup with no output schema, the description covers cost, the no-op/free path, the research fallback, and where the value actually surfaces. An agent can call it correctly and know what to do with the result in every branch.

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

Parameters3/5

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

Schema coverage is 100% and both parameters already document the mutual-exclusion rule and the search_people provenance, so the description's 'identified by exactly one of' largely restates the schema. Baseline 3 is appropriate since the schema does the heavy lifting with no added format or edge-case meaning.

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 ('Look up one person's mobile phone number') plus a hard identification constraint ('exactly one of person_id ... or linkedin_url'). It is immediately distinguishable from siblings like get_email or research_person.

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?

Explicitly names the alternative path: an unresearched person 'starts standard research_person' and returns a run_id, with the instruction 'do not call get_phone again' because the value arrives via get_research_status. It also points to search_people as the source of person_id, covering both when to use and when not to.

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