get_company_info

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does this well by stating a key guarantee—'NEVER returns any individual candidate data'—and explaining why ('the server holds none'). It also clarifies the meaning of index_built_at. The read-only nature is implied through 'Returns,' though it doesn't mention potential errors or authentication needs, which are secondary for this simple info tool.

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?

The description is two sentences with no wasted words. The primary purpose is front-loaded, return fields are listed concisely, and the critical negative constraint (no individual candidate data) is stated crisply. Every sentence earns its place.

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 tool with one simple parameter, no output schema, and no annotations, the description is largely complete. It names all return fields, explains the meaning of one potentially ambiguous field (index_built_at), and discloses the privacy limitation. It could go further by mentioning error behavior or how company_id is validated, but given the low complexity, the current information is adequate for correct invocation.

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?

The input schema provides zero description coverage for company_id, so the description must compensate. It only weakly ties the parameter to 'one employer,' but does not explain what a company_id is, where to obtain it, or expected format. This leaves the agent with only the tool name and the generic 'Company Id' title to infer the parameter's meaning, which is insufficient given 0% schema coverage.

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 'Aggregate, anonymous trust signals for one employer,' a specific verb+resource statement that immediately identifies the tool's function. It also enumerates the return fields (ghost_score_avg, active_jobs, index_built_at), and the scope ('for one employer') clearly distinguishes it from sibling tools like search_jobs, watch_intent, and authorize_application, which operate on different resources.

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 implied rather than explicit: the description says 'for one employer,' suggesting this is the tool to call when you need trust/aggregate signals for a specific company. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusion criteria or conditional guidance for selecting among siblings.

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