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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond them: 12 MB / 10 minute ceilings, the log_id return, per-field {value, source} shape under source verification, and HTTP 422 for unintelligible audio. It does not cover auth expectations or how to retrieve results after log_id.

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?

Roughly four dense sentences, front-loaded with verb+resource and then limits, return shape, error case, and usage. No sentence is filler; each adds a constraint or a routing cue.

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 an output schema present, return values need not be explained, yet the description still surfaces log_id and the source-verification field shape. Formats, limits, error behavior, and usage contexts are all covered; the missing piece is differentiation from claix.agent.audio and any async/retrieval guidance.

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%, so the baseline is 3. The description still adds meaning the schema lacks for the file inputs: the accepted audio MIME types and the max size/duration constraints, which directly govern what can legally be passed.

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+resource ('Extract structured JSON from spoken audio') and immediately constrains it with accepted formats and size/duration limits. An agent can distinguish it from claix.extract.pdf or claix.extract.image from the name and description alone.

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 for calls, meetings, voice notes, or dictations' gives clear positive context for when to reach for this tool. However, it never names an alternative or an exclusion, and the very close sibling claix.agent.audio is left un-differentiated, which is the main routing risk.

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