Skip to main content
Glama

Tommos

Read a company

get_company
Read-onlyIdempotent

Read one company, as its page shows it: its name, its domains (each with who added it), who renamed it, its status, its stage of prospecting with who moved it and the reason of «Not now», the hand-over of a picked company, how it came, its last touch, its live people with their status and whether each belongs by the domain of their mail or by a person's link, its deals with their stage, what the page offers a person (makeADeal, pick), the company's note (note: the one note each of its people shows) and the provider's figures of the company (figures: with when and by which domain they were fetched; null when none). Its evidence comes a page at a time, newest seen first, each fact with its link, date, the source's own words and the source, with the total and the sources that found it: the first 20 facts, or the page that evidence_offset and evidence_limit (max 200) ask.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "company_id": "<company_id>"
    },
    "name": "get_company"
  }
}

Input Schema

NameRequiredDescriptionDefault
company_idYesThe company's id (from list_companies)
evidence_limitNoFacts of the evidence on this page (default 20, max 200)
evidence_offsetNoFacts of the evidence to skip (default 0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuine behavioral context on top: evidence is returned a page at a time, newest seen first, 20 by default, and provider figures are null when none exist. It still does not say what happens with an invalid company_id or whether fields are omitted when absent.

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

Conciseness3/5

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

The content is dense and specific, and it is front-loaded with the verb and resource, but the body is one sprawling run-on enumeration of nested fields ('its ... with who ... and the reason of «Not now»') that is hard to parse on a single read. Every clause carries information, yet the structure works against comprehension.

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

Completeness4/5

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

There is no output schema, so the description carries the full burden of describing the return value, and it does so thoroughly: entity fields, evidence page shape with link/date/source words/total, and null semantics for figures. Given the tool is a read with only three parameters and no output schema, this is close to complete; only error behavior is unaddressed.

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%, so company_id, evidence_limit and evidence_offset are already documented, including the default 20 and max 200. The description only restates that these paginate 'facts of the evidence' and that ids come from list_companies, adding marginal clarification rather than new meaning. Baseline 3 applies.

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

Purpose4/5

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

The opening clause 'Read one company, as its page shows it' gives a specific verb and resource, and the enumeration that follows pins down exactly what is returned (domains, status, stage, deals, note, figures, evidence). It is distinguishable from the write-oriented siblings (rename_a_company, move_a_company, make_a_deal_on_a_company) and from list_companies, which the schema references as the id source. It loses a point because the sheer volume of enumerated fields blurs the core purpose rather than sharpening it.

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

Usage Guidelines3/5

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

Usage is only implied: the description signals 'this is the full page view of one company' by enumerating everything the page shows, and it explains that evidence arrives paginated. There is no explicit statement of when to prefer this over get_contact, get_deal, or the activity readers, and no prerequisites or exclusions are stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.