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

Annotations already flag destructiveHint/idempotentHint, and the description adds real context: underlying footage is preserved, a playable project is saved, unsupported changes are refused without rebuilding, the account's direct-edit allowance is consumed, and the call is free. That is meaningful disclosure beyond the structured safety flags.

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 core action and outcome, and every clause carries operational value (cost, refusals, retries). The telegraphic fragments ('Cost: Free: no credits.') are efficient but slightly clipped in style.

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?

Given an output schema, return values need not be explained; the description instead covers what an agent actually needs — prerequisites, versioning, side effects, refusal behavior, retry semantics, and cost. Nothing essential is missing for correct invocation.

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?

With 80% schema coverage the baseline is 3, and the description adds provenance: base_version and output_id come from get_project_context, and operation_id must be stable across retries. Minor friction in that the schema says output_id comes from check_video while the description points at get_project_context.

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 ('Remove one added overlay by its returned ov_ ID') plus the resulting state ('preserving underlying footage'), which cleanly separates it from put_video_overlay and remove_scene. The ID-pattern reference makes the target 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?

Explicitly prescribes the prerequisite sequence ('Read get_project_context first and pass its base_version and selected output_id') and routes to siblings for adjacent needs ('request a file separately with check_video with_download'). Retry guidance ('Preserve operation_id and exact inputs on retries') covers the main misuse case.

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