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

Annotations already declare idempotentHint=true, readOnlyHint=false, and destructiveHint=false, so the agent knows this is a non-destructive, idempotent write. The description adds the crucial async/polling pattern (poll get_transcription) and the 0.1–6s clip bound, which is behavioral context beyond the annotations. It does not state auth/permission requirements or what happens on boundary violations, so a 3 rather than higher.

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?

Short and front-loaded: the scope constraint leads, followed by the polling instruction and the manual-entry alternative. No filler, though the 'Optionally' framing and stray line breaks slightly muddy the lead.

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?

An output schema exists, so return values needn't be explained, and the async polling guidance is present. However, with four required, fully undocumented parameters and no annotation-conflicting or permission details, the definition leaves the agent unsure how to populate start_sample/end_sample and what idempotency_key requires.

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% and the description mentions only a 0.1–6-second duration limit. The four parameters (project_id, start_sample, end_sample, idempotency_key) are entirely undocumented; the description doesn't clarify that bounds are in samples, explain the idempotency key semantics, or map the 0.1–6s window to start/end sample values. Significant compensation gap.

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 (transcribe) and scope (words in a selected clip), and explicitly distinguishes it from full-song transcription. The 'Never the entire song' constraint is clear, though the 'Optionally' opener is a bit fuzzy since the required params suggest the operation isn't actually optional in itself.

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 names the follow-up tool (get_transcription) for polling, states the verification expectation (check against what you hear), and names an alternative path (manual lyric entry works without this step). This is exactly the when-to-use / alternative information an agent needs.

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