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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety bar is lower. The description adds one genuinely new fact, 'Cost: Free', plus the RFC 6902 mechanism, but says nothing about scope of destruction, the atomicity ('All or none' lives only in the schema), or how base_version interacts with concurrent edits.

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?

Two short clauses, no filler, and the mechanism is stated up front. 'Cost: Free' is slightly cryptic in isolation but does carry distinct information, so nothing is clearly 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?

Placeholder

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% with per-parameter descriptions (video_id defaults to the open video, base_version is 'version id you read', operation_id dedupes retries), so the schema does the heavy lifting. The description merely gestures at 'get_project's film' without adding syntax, versioning, or retry semantics beyond the schema.

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 concrete verb+mechanism ('RFC 6902 patch') and an explicit target ('get_project's film'), which lets an agent distinguish this generic mutation entry point from specialized siblings like add_clip or set_captions. The only weakness is the undefined term 'film', which the agent must infer equals the project document from get_project.

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?

'Any change' implies this is the universal escape hatch for edits, which is useful framing against the many narrow sibling mutation tools. However, it gives no explicit guidance on when to prefer a purpose-built tool (add_clip, set_captions) over hand-rolling a patch, and no prerequisites or when-not conditions.

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