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

Read-only/non-destructive safety is already covered by annotations, so the description adds only the policy semantic that an agent already seated in a chat stays and answers nobody — useful edge-case context. It does not describe the response envelope, error behavior, or cost. The added value is real but limited once annotations carry the safety profile.

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 opening question-format statement is front-loaded, but the remainder is a single dense run-on packing three field semantics, an edge case, and a permission rule into one sentence. It is efficient in length but poorly structured, making it harder to parse than separate labeled statements would be.

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 read tool with no output schema and annotation-covered safety, the description supplies the essential return-value semantics (mode, roles, mayChange) and the setter alternative, which is what an agent most needs. It stops short of return structure or failure modes but is adequate for a 0-param getter.

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?

With zero parameters, the baseline is 4, and the description goes further by explaining the meaning of the values the tool returns (mode defaults to 'all'; 'chosen' scopes to roles). That reframes 0-param semantics toward output meaning, which is beneficial.

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 conveys the resource and scope precisely — the policy controlling which company agents may participate in its chats — by enumerating the fields it yields (mode, roles, mayChange). It is not a tautology of the title and names the setter sibling set_chat_agent_policy, so it is distinguishable. However, the getter verb is never stated explicitly; the purpose is reconstructed from the field inventory rather than declared.

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?

It points to set_chat_agent_policy for mutation and notes mayChange reflects whether the company owner may alter it, which implicitly frames this tool's read role and a permission precondition. But there is no explicit 'use this tool when…' statement, no when-not guidance, and no suggestion to read mayChange before attempting a change — the routing is left to inference.

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