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

Annotations are present (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, yet the description still adds real behavioral context: PROJECT-SCOPED resolution of project_id, that it returns the project identity with the result, that it runs as 'One batch', that replan='mt1' re-plans an already-recorded montage, and that dry_run only shows slots. It stops short of saying what happens to pre-existing edits.

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 PROJECT-SCOPED and WRITE tags are usefully front-loaded, but the remainder is a dense run-on of production jargon crammed into two sentences. It packs a lot of value but reads as a wall of clauses, hurting scannability for an agent trying to extract the call 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 14-parameter scheduling tool with no output schema and low schema coverage, the description covers intent and much behavior but leaves many parameters unexplained and gives no return-shape information beyond 'project identity with its result'. It is adequate to understand what the call does, but not complete enough to invoke it confidently without reading the schema.

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 only 21% across 14 params, so the description must compensate and does so only partially: it documents style values (call_response, arc), modes values (strobe|pulse|hold), replan='mt1', and dry_run semantics, plus hints for on/clock ('kick', 'beat slot', 'speech stresses'). Params like seed, start, end, every, shots, music_id, and lead_f receive no meaning beyond the schema.

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 states a concrete verb and resource: it is a WRITE that lays a beat-synced montage over a program window on the user's track (or speech stresses when no track). That is specific enough to distinguish it from pure analysis tools like analyze_music or get_audio_analysis, but it never names a sibling (e.g. beat_align_cuts, plan_loop, shape_music) to sharpen the boundary, so differentiation is inferred rather than stated.

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 gives operational conditionals -- 'strobe only when the user asked for flashing', 'or the speech stresses when there is no track', 'replan=\'mt1\' re-plans a recorded montage', 'dry_run shows the slots' -- which imply usage. But there is no explicit statement of when to choose this over the many adjacent tools, and no when-not guidance. Usage is implied rather than directed.

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