crm_get_companyOne company, by id or name, with its tags, custom fields, people, deals (open ones first) and notes, each note with who wrote it (by and via, as crm_timeline gives them). An archived company is read too (archived: true). Free.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| company_id | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint/idempotent annotations, the description discloses the payload shape (people, deals with open ones ordered first, notes with by/via author attribution matching crm_timeline) and that archived companies are still returned. It also notes the call is 'Free', a cost signal absent from annotations. The gap is what happens when neither identifier is supplied, which matters since both parameters are optional.
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 dense sentence with the resource and lookup keys front-loaded, followed by the returned contents in decreasing relevance. No filler and nothing repeated from annotations.
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?
With no output schema, the description usefully sketches what comes back and how notes/deals are ordered, and annotations already cover the safety profile. The remaining gap is the zero-required-parameter ambiguity: an agent cannot tell from the description what the tool does if both name and company_id are omitted.
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 carry the meaning of both parameters, and 'by id or name' does establish that the two are alternative lookup keys rather than joint requirements. However it gives no format, matching, or precedence guidance (e.g. which wins if both are passed, whether name must be exact), and the '(archived: true)' parenthetical is ambiguous since no such parameter exists.
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 opens with a concrete verb and resource ('One company, by id or name') and then enumerates the related data returned (tags, custom fields, people, deals, notes). It clearly signals a single-record fetch as opposed to a search, though it never names a sibling like crm_find_companies to sharpen the distinction.
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?
Usage is only implied — 'One company, by id or name' suggests a direct lookup once an identifier is known, and the note about archived companies hints at a visibility case. There is no explicit statement of when to prefer this over crm_find_companies or crm_search, nor any prerequisite for obtaining the id/name.
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.