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

Annotations already provide readOnlyHint=true and destructiveHint=false, so safety profile is covered. The description adds valuable behavioral context: it does not score emotion or tone, returns time-ordered segments and word timings, and places constraints on input size/format. It does not fully explain pagination or return structure, but with readOnlyHint covering side-effect transparency and the description covering output structure, this exceeds the baseline for annotation-covered tools.

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 sentences, each earning its place: what the tool does, when to use it, and constraints/formats. It is front-loaded with the core purpose and routes to siblings at the end. No wasted words.

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 6-parameter tool with no output schema, the description covers input format, size limits, duration limits, and output shape (time-ordered segments, word timings) and differentiates from siblings. It doesn't explicitly describe the exact response JSON structure, but without an output schema and with rich schema/annotations, this is well above minimum viability. Returning exact response fields might be a small gap, but it does not compromise safe invocation.

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 adds value by mapping parameters to behavior: compact vs full detail, audio_url vs audio_base64 size limits, and clarifies that api_key is only for trial keys. It reinforces parameter meaning beyond the schema's per-parameter text, earning a 4.

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?

The description opens with a specific verb ('Transcribe prerecorded English audio to text') plus resource (audio) and output specifics (time-ordered segments, word timings). It explicitly differentiates from siblings by stating when to use transcription vs. tone/analysis, so an agent can distinguish it from oruk_analyze_speech and oruk_analyze_tone without opening the 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?

Gives explicit usage direction: 'Use this when only the words matter,' and names alternatives with conditions ('use oruk_analyze_speech for transcript + tone together, or oruk_analyze_tone for tone alone'). This is clear when-to-use and when-not-to-use guidance, beyond anything in the schema.

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