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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true) by disclosing the critical failure mode: the server never receives conversation-attached files or local paths. It warns that chunking/re-encoding is futile because 'the obstacle is the transfer, not the size,' which prevents the agent from wasting effort on doomed workarounds. No contradiction with 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?

Roughly 120 words, but every sentence earns its place: purpose, parameter format, usage condition, sibling alternative, hard constraint, remediation, and an anti-pattern warning. Content is front-loaded with purpose and progresses in a logical paragraph structure.

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?

Since an output schema exists, return-value details are not needed. The description handles the tool's complexity well and even covers failure modes. The lone gap is the language parameter, which is undocumented in both the schema and the description — a minor miss for a two-parameter tool.

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 0%, so the description carries the burden, and it does fully define the audio parameter as 'an https URL or base64 audio' — meaning beyond the schema's bare 'string' type. However, the language parameter is never mentioned; its purpose, format, and effect are left entirely to inference.

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?

Opens with a clear verb+resource statement, 'Transcribe a recording,' and defines what the audio input accepts. It distinguishes itself from the closest sibling, summarize_recording, by noting this tool returns literal text for short recordings while the sibling adds speakers and tone.

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?

Explicitly states when to use this tool ('Use this for short recordings when you want the literal text') and when not to ('For anything past a few minutes prefer summarize_recording'). It also names the sibling, explains the cost difference, and instructs the agent to ask the user for an https URL when a local file is involved.

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