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

Annotations only declare readOnlyHint=false, so the description carries the real load and does it well: it discloses the invariants (pair length fixed, all other elements untouched, footage in/out follow), the ordering contract, and the exact refusal conditions with a named fix. The note that a refusal returns the delta_ms range that fits is unusually actionable behavior detail.

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?

One dense paragraph, front-loaded with the core operation before the topology rules and then the failure modes. Every sentence carries distinct information: mechanics, invariant, valid pairing, refusal list. No filler or repetition of the schema.

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 four-required-parameter mutation tool with no output schema, the description covers everything an agent needs: what changes, what stays fixed, valid inputs, and how failures are surfaced. The absence of return-value documentation is acceptable since the schema declares no output.

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 100%, so baseline is 3; the description adds genuine meaning by explaining the sign convention for delta_ms, what left_id/right_id mean relationally (they must share a cut), and the 100ms floor and cap/footage ceilings that no schema field encodes. It does not spell out units/format for project_id beyond what the schema says, but that is minor.

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 gives a precise verb-plus-resource ('Move the cut between two neighbours by delta_ms') and pins down the exact mechanics: left's end and right's start move together with their footage points, total length unchanged. That is far more specific than a name restatement. It loses a point only because it never names the adjacent edit operations (slide_edit, slip_edit, trim_clip, shift_clips) that an agent could plausibly confuse it with.

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 valid topology clearly: the pair must be a scene and the next scene, or two touching clips on one track, left one first. Refusal cases (unknown id, no shared cut, locked track, out-of-range delta) further bound when the tool applies. There is no explicit 'use X instead when Y' routing to sibling edit tools, which keeps it short of a 5.

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