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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond them, disclosing the full return shape (transcript, confidence, language, duration, per-word start/end times), the billing model (2 credits, charged only on success), and the two accepted input channels. That is exactly the behavioral context annotations cannot carry.

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?

Purpose is front-loaded in the first sentence, return values second, routing guidance third, input and cost last. Every sentence carries distinct information with no filler.

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 no output schema, the description compensates by enumerating the return fields, and it covers cost, input channels, and sibling routing. An agent has everything needed to select and invoke the tool correctly.

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 restates the audio_url vs audio_base64 choice as 'or', which adds mild clarity on input alternatives but no syntax, format, or size limits, and it says nothing about the language parameter.

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 ('Transcribe audio to text with timestamps') and immediately differentiates itself from the siblings transcribe and subtitle by naming both and the conditions that select them. An agent can route among the three transcription-family tools 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?

Explicit when-to-use ('a short clip whose exact words and timings you need') plus two named alternatives with their own selection criteria: transcribe for long multi-speaker recordings, subtitle for caption files. Nothing 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.