Restore project

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

With only idempotentHint in annotations, the description carries the burden well: it discloses the no-op on non-deleted projects, the account-cap refusal, the processing→failed outcome, and the exact return shape { changed, status }. These are behavioral traits not derivable from structured fields.

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?

Three compact sentences, each earning its place: action, lookup+no-op, refusal, failure path, and return value. Front-loaded with the primary action and no filler.

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 mutation tool with no output schema, the description covers preconditions (must be deleted, cap limit), edge outcomes (processing→failed), and the return payload. Nothing an agent needs to invoke it correctly is missing.

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 100% and the id parameter is already documented, so the baseline is met. The description corroborates the source of the id ('from list_deleted or list_projects deleted: true'), adding a small locating hint but little 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 specific verb+resource ('Bring back a deleted project') and adds scope ('with its clips and files'), which clearly separates it from sibling restores like restore_clip and restore_asset. An agent can identify the operation 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?

Explicitly names where to locate the target ('find it with list_deleted or list_projects deleted: true'), states the no-op case for non-deleted projects, the refusal case at the live project cap, and routes to retry_project for projects that come back failed. When/when-not/alternatives are all covered.

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