Detect Beats

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

With annotations nearly empty (readOnlyHint=false and no destructive flag, so no safety signals), the description carries the full burden and does so admirably. It discloses the non-destructive nature, the 30-minute decode limit, the bounded mono analysis stream, the local onset autocorrelation method, and the exact return content. This gives an agent strong behavioral expectations without needing to guess.

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?

Three sentences, each adding substantive information: non-destructive scope, input/time limit, algorithm, and outputs. The most important facts are front-loaded, and there is zero redundant filler or repetition of the schema field descriptions. Every term ('bounded mono analysis stream,' 'phase-aligned') earns its place by sharpening the behavioral contract.

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?

For a two-parameter tool with a rich output schema, the description covers all the operational essentials: input type, duration cap, analysis strategy, output dimensions, and side-effect absence. The output schema handles the return structure, so the description need not enumerate fields. The only minor edge case (what happens when the file is longer than 30 minutes) is not stated, but it is a small gap in an otherwise complete definition.

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?

The input schema already documents both parameters completely (100% coverage): media_path is 'Absolute path to an existing local audio or video file' and max_beats is 'Maximum beat times returned (default: 500).' The description adds useful context by explaining the file is decoded by FFmpeg and that beat times are phase-aligned, which gives the path meaning beyond just 'a file.' It does not fully explain max_beats, but that is already explicit in the schema, so a 4 is warranted rather than 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?

The description does not just name the tool; it specifies a concrete verb and object: 'Estimate a steady beat grid from a local audio or video file.' It also names the key outputs (BPM, beat times, confidence, half/double-time alternatives), which makes the tool's purpose unmistakable and distinguishes it from detection siblings like detect_silence, detect_audio_transients, and detect_motion_peaks.

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 description establishes clear usage context: use this tool when you need a beat grid from a local media file, and it explicitly scopes the operation as 'without changing Premiere.' The written output contract (BPM, phase-aligned beat times, confidence) makes it clear this is for beat-oriented analysis, not general transient or silence detection, so an agent can correctly choose it among many detection tools.

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