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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds substantive context beyond them: the edit persists as a playable project, unsupported changes are refused without partial rebuilds, operation_id must be preserved on retries, the call consumes the account's direct-edit allowance, and it costs no credits. The only gap is not spelling out what an 'update' does to unlisted properties of an existing overlay.

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?

Purpose and allowed kinds are front-loaded, then prerequisites, persistence semantics, failure behavior, retry rules, and cost in a tight sequence of short sentences. Slightly telegraphic phrasing ('Cost: Free: no credits') is dense but each sentence carries distinct information, so little is wasted.

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 destructive, version-guarded mutation with an output schema present, the description covers everything an agent needs before calling: required prior tool, ID sources, concurrency token, idempotent retry protocol, refused-change behavior, and quota/cost. Return-value details are correctly omitted since an output schema exists.

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 80% and four parameters already carry descriptions, so the baseline is 3. The description goes above that by explaining the overlay kinds (text/image/video) that drive the untyped oneOf and their animation enum, and by tying base_version/output_id to get_project_context so the agent knows where those values come from.

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+resource+scope: 'Add or update one timed text, image or video overlay', and enumerates the animation types. An agent can distinguish this from remove_video_overlay by the verb, but no sibling is named explicitly, so differentiation is implicit 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?

Gives explicit prerequisites ('Read get_project_context first and pass its base_version and selected output_id'), constrains inputs ('Use only existing canvas asset IDs and editable capabilities returned by the project'), and routes elsewhere for the follow-on need ('request a file separately with check_video with_download'). This is clear when-to-use and when-to-use-something-else guidance.

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