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

Annotations already declare the safety profile (idempotent, non-destructive, closed-world), and the description adds real behavioral context beyond them: the source_in anchor, the fact that linked clips are also swapped by default, that linked:false scopes it to this clip only, and that clip_ids enumerates every clip affected. The remaining gap is that it defers the actual return payload to 'the server instructions' rather than describing shape.

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 tight sentences, front-loaded with the core operation and its invariants, with the linked-clip caveat placed after. The parenthetical '(see the server instructions)' is a small punt but compact rather than wasteful.

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 an idempotent, non-destructive mutation with 6 params, 83% schema coverage and an output schema, the description covers the essentials: what changes, what is preserved, side effects on linked clips, and the source_in anchor. The pointer to server instructions for the return payload is acceptable given an output schema exists, though it costs a bit of self-sufficiency.

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 83%, so the schema already documents most parameters well. The description largely restates schema content ('Starts at source_in (default 0)', 'linked: false for this clip only') rather than adding format or edge-case meaning; the one genuinely new semantic, clip_ids listing all swapped clips, is an output rather than an input.

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 verb ('swap the media') and resource ('in a clip') are specific, and the description pins down exactly what is preserved — place, length, speed, look — which separates it from remove-then-add or clip.add workflows. It does not name a sibling tool to route away to, but the operation itself is unambiguous.

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?

Usage is implied by the description: use it when you want a different media asset in an existing slot rather than a new clip. There is no explicit 'use X instead when…' guidance versus clip.add, clip.trim or clip.remove, and no stated prerequisites (e.g. that media_id must be imported first — that only appears in the schema).

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