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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description still adds real behavioral context: one grid image rather than N images, per-cell visibleClipIds plus nonBlankRatio and fingerprints, automatic cellHeight shrinking under a response budget with a note in the reply, and the cost tradeoff of enabling pixels. This is context an agent could not infer from annotations or schema.

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?

Front-loaded with the verb and output shape, then guidance, then the cheap-sweep tip — a logical progression with little waste. Some all-caps emphasis and the SAMPLE paragraph are slightly verbose for the amount of novel information, keeping it just under top marks.

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 carries the return-value burden and does so fully: the contact-sheet grid, labelled cells, visibleClipIds, fingerprint, nonBlankRatio, and the budget-shrink notice. For a 7-parameter render tool it tells the agent everything needed to call it and interpret the result.

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 the baseline is 3, but the description adds genuine semantic guidance on two parameters: frames should be sampled at cut points and section middles (not just frame 0), and pixels:false trades image cost for structure plus fingerprints. It stops short of restating columns/cellHeight/format details, which the schema already handles.

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?

States a specific verb and resource — composites every video layer at requested frames and returns a single contact sheet with per-cell visibleClipIds and fingerprints. It explicitly distinguishes itself from get_timeline ('shows what actually PLAYS, as opposed to what get_timeline says is arranged'), so an agent can route without opening either 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?

Gives concrete when-to-use ('Use it to check an edit'), a concrete sampling strategy ('sample the cut points and the middle of each section, not only frame 0'), and a cost-based alternative mode ('use pixels:false for a cheap sweep'). It also names the sibling it is not, closing the loop on the decision.

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