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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is known. The description nonetheless adds concrete value by specifying the blast radius (the parent entity and all rendered clips plus their underlying files) and reinforcing irreversibility. It stops short of saying what happens to in-flight renders or whether auth elevation is required.

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 sentences, no filler, with the destructive verb front-loaded and the irreversibility statement closing. There is no padding or repetition of the title.

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 single-parameter destructive tool with no output schema, annotations cover safety and the description covers destruction extent, so the core is adequate. What is missing is disambiguation of the target entity ('project' vs 'clip request') and any note on what happens to an active render job, which is material for an irreversible operation with no undo sibling.

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 0% and the description never mentions the single requestId parameter, what it identifies, or accepted format. It also does not clarify whether the UUID refers to a clip request or a clip, which matters because the description's noun ('project') differs from the parameter name. With no compensating text, an agent must infer everything from the parameter name alone.

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?

The verb and scope are specific ('Permanently delete... all its rendered clips (and their files)'), which goes beyond the title. However, the description calls the target a 'project' while the name, title, and sibling tools (get_clip_request, rename_clip_request, list_clip_requests) establish the resource as a 'clip request'. That noun mismatch leaves the agent unsure whether 'project' is a synonym or a different entity whose clips are being deleted.

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?

No when-to-use guidance, no prerequisites, and no alternatives are named. Given siblings like rename_clip_request and cancel_scheduled_post, an agent gets no help deciding whether deleting is the right action versus renaming or cancelling. Only the implicit 'this destroys things, be careful' framing is present.

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