Analyse against a profile

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

With no annotations the description carries the full burden and does well: it discloses the paid-plan gating for seven profiles, that only the required passes execute, that results are keyed by stable lens id, and that series:true produces a 'much larger payload' to leave off unless read. It stops short of rate limits, latency, or failure behavior, but the cost/entitlement tradeoffs are unusually well surfaced.

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?

Purpose and profile list are front-loaded and the audio-source note closes it out, so it reads in the right order. It is somewhat dense and run-on (the series sentence and 'values,a much larger payload' are slightly garbled), which costs a point but not much material clarity.

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 describe returns: it explains results are keyed by stable lens id, scoped to only what the profile needs, and optionally augmented with curves, per-block lanes and per-phrase values. That covers the shape at a high level, though it does not enumerate per-lens fields, so an agent can call it correctly but not fully predict the payload.

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%, so baseline would be 3, but the description adds real semantic value the schema lacks: the enum's terse 'Which question to answer' is expanded into a concrete question per profile value, and the series flag's payload consequence is explained rather than merely described.

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 ('Measure a file against a named working set of lenses') and then enumerates the eight profiles with the exact question each answers, which lets an agent distinguish this multi-lens entry point from single-purpose siblings like analyze_loudness or analyze_voice.

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 per-profile question list implies when each profile is appropriate, and it notes 'only the analysis passes the profile needs are run', which is useful routing context. However it never states when to prefer this tool over sibling analyzers (analyze_voice, analyze_loudness) or when a profile is the wrong entry point, so guidance remains implied rather than explicit.

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