analysis_compare

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

Annotations already cover safety (read-only, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavior: both inputs must be finished captures, results are ordered strongest-first, and the intended remediation path is an EQ cut set up via two other 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?

Two sentences, zero padding. The scenario and the returned axis come first, and the recommended fix is tucked into a trailing parenthetical rather than competing with the core statement.

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 convey the return value, and it does in summary form: per-band levels plus the bands where both sources sit within a few dB, sorted strongest first. Exact field names and units are left unstated, which keeps it from a 5.

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 coverage is 100% and both parameters are documented as job ids, so the schema does the heavy lifting (baseline 3). The description contributes the additional constraint that the referenced jobs must be *finished* captures, which is meaning the schema does not encode.

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 concrete verb-and-resource: comparing two finished captures band by band, returning levels and overlapping-energy bands ordered strongest first. The musical examples (kick/bass, vocal/guitars) make the resource unambiguous. It does not name a sibling to contrast with, so it stops short of 5.

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 framing "where two finished captures compete" implies usage and implies the inputs must be completed analysis jobs, and it points at follow-up tools (devices_add EQ + devices_set_params) as the cure. But it never says when not to use it or how it differs from analysis_capture / analysis_file, leaving the agent to infer the workflow position.

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