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

Annotations only declare the read/write/idempotency profile; the description adds far more: it stores/replaces the beat grid, sound >=8s costs no credits while other ranges bill ~1.1 credits/minute by the second, and range beats replace the grid's beats in that range. It also documents an unusual binding contract ('bind with beats= in film props') not visible in structured fields.

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?

Well front-loaded (purpose, returns, then when-to-use and cost) and every clause carries semantic payload, but the mid-section is a run-on with an awkward construction ('A sound file of 8 seconds or more was measured when it arrived: its answer also has...'). Dense phrasing costs readability rather than wasting words.

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 fully compensates by enumerating return payloads (beats, downbeats, sections, hits, fills, big hits, drops, per-second loudness) and covering cost, replacement semantics, null handling, and the film-prop binding. An agent has everything needed to call it correctly.

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 75% and the description adds real meaning on top: startTime/endTime define the read range, drive billing, replace that slice of the grid, and 'null for both reads the whole file,' plus 'times stay seconds into the asset.' It adds little about assetId beyond the schema, keeping it off a 5.

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 ('Detect beats and bars in ready music or video; stores the grid') and enumerates the outputs (beat times, downbeats, sections, drum hits, fills). An agent can distinguish this from detect_scenes/analyze_video without opening either schema.

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?

"Do this before cutting to music" gives a clear trigger, and the description spells out the conditional branch (sound >=8s vs. video/shorter sound requiring startTime/endTime). It never names an alternative sibling tool or when *not* to call this, so it falls short of a 5.

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