get_r_company_agents

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

No annotations are present, so the description carries the transparency burden. It communicates a read operation via the word "Retrieve" and the `GET` endpoint, but it doesn't mention auth requirements, idempotence, possible error conditions, or any side effects. The implicit GET supplies basic transparency but not the depth a unannotated mutation could need.

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 short and front-loads the primary verb and endpoint in the first sentence. The second sentence quickly lists where to put each parameter class. Minor grammatical awkwardness and the generic level of parameter guidance are the only structural shortcomings; it is otherwise tight.

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 zero annotations and 0% schema description coverage, the description needs to tell an agent everything needed to call the tool safely and correctly. It only says buses orders, which filters/pagination format, and what headers are required; it also doesn't clarify what an "agent" is in this context or which route IDs might be expected. The presence of an output schema helps on the response side, but the most important invocation details about query structure and path parameters are still unspecified.

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 coverage is 0%: the four parameters are generic objects with no description. The description partially compensates by saying `route IDs` go in path_params and `filters and pagination` go in query, which adds meaning to those bare object containers. But it leaves the specific filter names, pagination format, and which headers are mandatory undocumented, so it doesn't fully bridge the coverage gap.

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 states "Retrieve agents" and includes the explicit endpoint `GET /r/company/agents` , giving a clear verb+resource pairing. It doesn't explicitly contrast with `get_r_company_agents_id`, but the endpoint path and collection-oriented phrasing make the list-vs-detail distinction inferable from siblings.

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?

The description gives placement guidance: route IDs in `path_params`, filters and pagination in `query`, and required headers in `headers`. However, it never says when to use this tool versus `get_r_company_agents_id` or any alternative, and it does not state exclusions or conditions, so the guidance stops at mechanical routing rather than decision support.

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