audio_compare

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral detail beyond that: the null test aligns and subtracts, and its verdict categories (identical, gain-changed, lightly or heavily changed) tell the agent what conclusions the tool can reach. It does not disclose format support or behavior on mismatched lengths/rate, which keeps it at 4.

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?

Two sentences, front-loaded with 'A/B two files' before the output enumeration, and the usage directive lands at the end. The long parenthetical output list is dense but each item is substantive rather than filler, so it earns its space without being wasteful.

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?

There is no output schema, so the description must carry the return-value burden, and it does so thoroughly by enumerating the report components. Combined with read-only annotations, safety is covered. The remaining gap is the totally undocumented pair of path parameters and unsupported edge cases (mismatched durations/sample rates), which leaves it just short of complete.

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 two properties carry only boilerplate titles ('Path A'/'Path B'). The description's 'A/B two files' wording implies path_a is the reference and path_b the candidate, which is mild added meaning, but it never specifies path format, required presence, or supported file types, so it only partially compensates.

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+resource ('A/B two files') and then enumerates concretely what the comparison surfaces (metric deltas, per-band levels, spectral similarity, null test). An agent can distinguish this from siblings like audio_analyze or audio_info because the paired-file comparison and null-test framing are unique to this tool.

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 gives context: 'Use after audio_process to verify an edit did what you intended and nothing else.' That is a clear when-to-use signal tied to a workflow. It stops short of naming alternatives (e.g., when to reach for audio_analyze instead) or stating exclusions, so it is a strong 4 rather than a 5.

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