Notes From Audio Loop

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

With no annotations, the description carries the full behavioral burden. It discloses the core algorithm—averaging step-note grids, filtering by min_presence and min_rel_db, tiling over write_bars—and explains that non-repeating artefacts drop out. However, it does not clarify whether existing notes are replaced or appended, what the default 'replace' mode actually does, or any permission/side-effect constraints. This leaves significant mutation semantics ambiguous.

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?

The description is dense but well-structured and front-loaded with the core concept ('Consensus transcription'). The second paragraph on loop variants is a useful special case, not filler. It is appropriately sized for a complex algorithm, though it could be slightly tighter.

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?

The description gives a solid overview of the consensus workflow and the loop-variant case, which is useful for a complex tool. However, it leaves critical parameters (especially mode) and mutation side effects unexplained, and with no annotations or schema descriptions those omissions matter. An output schema exists, so return values need not be covered.

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% with 15 parameters. The description adds meaning for several key parameters (source, bars, loop_bars, min_presence, min_rel_db, write_bars, base_bars), but leaves many undocumented: low, high, mode, track, project, rel_db, floor_db, and min_steps. For a 15-parameter tool with no schema descriptions, this partial compensation is insufficient.

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 opens with 'Consensus transcription' and specifies the resource (notes from audio) and the exact method used. It explicitly distinguishes itself from the sibling tool notes_from_audio by saying 'prefer it over notes_from_audio.' An agent can tell exactly what this tool does without opening the 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?

It states the intended context ('Use for loop-based music') and the alternative ('prefer it over notes_from_audio'). It also provides a special usage case for loop variants, including the condition ('the song alternates two versions of its loop') and the required parameter change ('pass base_bars = the whole span'). This is explicit when-to-use and alternative guidance.

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