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

Annotations declare readOnlyHint=false and idempotentHint=false but say nothing about the mode switch; the description supplies that nuance ('WRITE when write=true (else READ)') plus the fact that the call returns the project identity alongside its result. It adds real behaviour beyond the annotations, though it says nothing about reversibility or cost of the write path.

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?

Everything is packed into one dense block with the scope constraint front-loaded and no filler sentences. It is terse to the point of being hard to parse on first read, but each clause carries distinct 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 steps in to say what comes back (project identity plus result) and what the inserts look like. For a 6-parameter tool it covers nearly every input except `n`, so an agent has enough 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 description coverage is only 17%, so the description has to carry the load — and it largely does: it defines `write` (mode switch), `at` (program seconds, snapped to a cut), and all three `kind` values with their visual meaning, and hints at `accelerate` via 'accelerating'. Only `n` (number of inserts) goes unexplained.

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 names a concrete output — 'a rhyming sequence' — and enumerates the three variants (face_aligned, shape_chain, same_framing) rendered as 'cropped, muted inserts spliced at at'. That is specific enough to separate it from neighbours like find_shots or beat_align_cuts, though it never states plainly that it proposes (rather than applies) edits.

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 the crucial write-vs-read rule ('WRITE when write=true (else READ)') and the project-scoping requirement, which is genuine usage guidance. But it never says when to reach for this tool instead of the many adjacent suggestion tools (suggest_motion_beats, suggest_story, beat_align_cuts), so the routing decision is left to inference.

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