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

Annotations declare destructive/idempotent/not-readOnly, and the description adds genuinely new behavior: it saves a playable project rather than producing a file, unsupported changes are refused without rebuilding, the operation consumes the account's direct-edit allowance, and operation_id must be preserved on retries. These are exactly the traits an agent needs before calling a destructive mutation.

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-loads the action and scope, then prerequisite, side effects, retry, and cost in short sentences with no obvious filler. The telegraphic style ('Cost: Free: no credits') is slightly clipped but still efficient.

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?

Output schema exists and annotations cover the safety profile, so the description only needs to cover prerequisites, side effects, retry/idempotency, and cost – all of which it does. A destructive mutation with a required sequencing dependency is fully explained.

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 description coverage is 100%, so the schema already documents words, video_id, output_id, base_version, and operation_id. The description adds only the sourcing hint that base_version and output_id come from get_project_context; with the schema doing the heavy lifting, baseline 3 is appropriate.

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 footage time for the inclusive transcript word range') and explicitly distinguishes it from the nearby layer-removal operation ('This removes speech, unlike removing a graphic layer'). An agent can tell what it does and what it is not without opening the 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 a concrete prerequisite sequence ('Read get_project_context first and pass its base_version and selected output_id') and routes file retrieval to a sibling ('request a file separately with check_video with_download'). It lacks an explicit statement of when not to use it versus the layer/scene removal siblings beyond the speech distinction, so not quite a 5.

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