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

The annotations are all false (readOnlyHint=false, idempotentHint=false, etc.), so they convey only what the operation is NOT. The description adds genuine behavioral context beyond them: utterances are queued and played sequentially, calls before connection fail with session_not_connected, and an api_key is mandatory. No contradiction with the annotations.

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?

Three compact sentences, each carrying distinct information: purpose plus ordering semantics, connection precondition plus error case, and authentication requirement. The purpose is front-loaded and there is no filler or repetition of schema content.

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 low-complexity tool with three flat required parameters, the description covers purpose, queue semantics, the connection precondition, the error result, and authentication. The main gap is that no output schema exists and the description never mentions the return/response shape, which an agent might need to evaluate the outcome of the call.

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 67% (session_id has no schema description). The description compensates partially: it links text to the queueing behavior, explains that api_key is the key issued at signup ('signup で受け取ったキー'), and frames session_id as the session whose avatar will speak. session_id remains the least-specified parameter in both the schema and the description.

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?

States a specific action with a clear verb and resource: 'セッションのアバターにテキストを喋らせます' (makes the session's avatar speak text), including the scoping nuance that utterances are queued and spoken in order. The action is unique among the 20 sibling tools — the only related one, interrupt, is plainly a different operation, so there is no ambiguity.

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?

Gives an explicit temporal precondition — call only after the browser SDK connects via 'session.start' — and discloses the failure mode for violating it ('接続前は session_not_connected になります'). It does not name sibling alternatives (e.g., interrupt to stop speech), so it stops short of full routing guidance, but the when-to-use context is clear.

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