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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds useful behavior ('cached', timestamps on the selected source asset's clock). It omits what happens on a cache miss or stale analysis, and 'cached' sits in mild tension with idempotentHint=false, though not enough to constitute a contradiction.

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 with no filler; the payload summary comes first and the timestamp caveat second. Nothing could be removed without losing information.

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?

With no output schema, the description must carry the return shape, and while it lists the feature categories it gives no structure (are beats timestamps, intervals, counts?), no units, and no error/cache-miss behavior. For a read tool with an undocumented asset_key, this leaves real gaps an agent would want closed before calling.

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 50%: project_id is documented in the schema, but asset_key is bare. The description only implicitly hints that asset_key selects the source asset whose clock is used ('the selected source asset's clock'), and never says whether asset_key is optional or what the default is. Baseline 3 is appropriate given partial schema documentation.

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 resource ('Returns cached measured audio features') and enumerates the concrete payload (tempo and confidence, beats, energy changes, stressed words), which is far more informative than the title alone. It does not, however, distinguish itself from measurement-adjacent siblings such as analyze_music, get_syllables, or get_words, so an agent must infer that this is the read/cached side rather than a fresh analysis.

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?

There is no when-to-use guidance at all: nothing says whether analysis must be produced first (e.g., by analyze_music), whether a missing analysis errors or returns empty, or when to prefer get_syllables/get_words/get_editorial_map over this tool. The agent is left to guess from the word 'cached'.

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