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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral transparency beyond that: it discloses scope limits (≤30 MB / ≤60 min, English), states that predictions are 'calibrated acoustic annotations of delivery, not claims about inner state,' and clarifies it does not transcribe. This is exactly the kind of context that shapes an agent's expectations.

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?

The description is compact and front-loaded: it leads with the central claim, then the use-case, then constraints, then the sibling routing. Three sentences earn their place with no filler. It avoids listing what's already in the schema and keeps the important disambiguation near the top.

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?

The description covers purpose, scoping, constraints, and sibling routing, and the schema fully documents the six parameters with 100% coverage. The only area it does not cover is the return format, but there is no output schema and the tool's outputs are simple enough that the 'calibrated labels per segment' description is sufficient. The missing details are already captured in the schema and semantics it does not need the description to repeat.

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 explaining the tradeoff between audio_input and audio_url, the consequence of choosing one over the other ('Prefer audio_url for anything larger'), and the language constraint. It doesn't deeply explain the model or detail args, but the schema already does that well. The description complements the schema without being redundant.

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 clearly states a specific verb and resource: 'Score how speech sounds without transcribing it' — this is not a tautology. It explicitly distinguishes itself from a sibling tool (oruk_analyze_speech) by saying 'Need the words too? Use oruk_analyze_speech.' The agent can understand exactly what this tool does and what it does not do.

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 usage guidance is provided: 'Use this when the user asks about mood, delivery, sentiment, sarcasm, or emotional dynamics in audio.' It also explicitly names an alternative and the condition for choosing it ('Need the words too? Use oruk_analyze_speech'). This is a model example of routing the agent to the right tool.

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