compare_audio_files

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds only that the output is objective rather than a quality rating. It says nothing about how the comparison is performed or why a read-only comparison exposes dry_run, confirm_delete, max_seconds and expected_revision at all, which is the one behavioral puzzle an agent would need resolved.

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?

It is a single front-loaded clause plus a negation, so there is no wasted wording. But the terseness is under-specification rather than economy: given six undocumented parameters, the description is too small for the tool's complexity.

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 need not be described, but the definition leaves the input contract entirely unexplained despite 0% schema coverage and a nested request object with mutation-flavored fields. For a comparison tool an agent would still not know what to pass as first/second or what dry_run/confirm_delete do here.

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% across six nested fields, and the description supplies no meaning for any of them — not for first/second (what constitutes a valid pass identifier), not for max_seconds, not for confirm_delete on an allegedly non-destructive operation. The schema titles and constraints are the only signal available.

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 verb "Compare" is specific and the object is bounded to two inputs, but "measured passes" is unexplained jargon and does not clearly connect to the tool name's "audio files" or distinguish this from analyze_audio_file. An agent can guess the purpose but cannot state precisely what a "pass" is or what dimension is being compared.

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?

The clause "no subjective quality score" implies a when-not (don't use this for subjective assessment), but it never names the alternative for that job, nor states prerequisites such as both files needing to be measured passes of the same source. No explicit when-to-use guidance is given.

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