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

Annotations already cover the safety profile (idempotent, non-destructive, open-world), so the description's added value is the stage-isolation semantics and the return shape ('returns timed segments'). It does not say whether the call is synchronous or returns a job to poll, which matters given the lunara_get_job sibling — that is the one meaningful behavioural gap.

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 short sentences, front-loaded with the capability and the exclusion, then the return value, then the selection rule. No filler or restatement of the title.

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 two-parameter tool with no output schema, the description supplies what the schema cannot: what comes back (timed segments) and that this is a single pipeline stage. The remaining omission is job/lifecycle behaviour, which an agent calling a transcription service likely needs to know.

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 100% and both parameters (audioUrl, spokenLang) are documented in the schema itself. The description adds nothing about either input, which is acceptable at full coverage but is the baseline, not a contribution.

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 verb and resource ('Run speech recognition') and immediately scopes it by negation — 'no rewrite, no translation' — which separates it from lunara_rewrite and lunara_translate. An agent can pick this over its siblings without opening any schema.

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?

'Use this when you want the transcript itself, or when you plan to pick a later stage yourself' gives a clear positive selection condition. It doesn't name the specific alternative tools (lunara_subtitle_from_url, lunara_start_subtitle_job) for the case where the caller wants the full pipeline in one shot, so routing is implied rather than explicit.

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