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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuinely non-obvious context: the output separates proposed impacts from measured references, and it explicitly confirms no audio is produced. It says nothing about how corpus widening behaves, which is a remaining gap.

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 dense sentences, front-loaded with the verb and artifact, then output composition, then the epistemic caveat. No filler and nothing restated from the title.

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 description conveys the artifact's nature well. But for a tool with four parameters, nested objects, and zero schema descriptions, leaving filters and allow_broaden entirely unexplained is a real completeness gap.

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 schema is deeply nested, so the description must compensate. It only covers the required `plan` argument in passing and never mentions `filters`, `min_videos`, or `allow_broaden` — the last being a consequential corpus-widening switch an agent cannot infer.

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 and artifact ("Build a musical brief from a plan") plus what the brief contains (corpus BPM/voice-bed distributions, timed energy arc). This clearly distinguishes it from data-returning siblings like corpus_stats or plan_structure, though it never names them explicitly.

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?

Usage is only implied: "from a plan" signals the required input and "no audio is generated" routes the agent away from generation tools. There is no explicit statement of when to choose this over reference_brief, critique_plan, or corpus_stats.

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