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

Annotations already declare destructive/non-idempotent, so the safety bar is covered; the description adds the non-obvious part — three refusal conditions and the required permission scope. It stops short of saying whether the deletion is recoverable or what confirmation flow exists, which would have pushed it higher.

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 clauses, front-loaded with the action and scoped by the refusal rules; no filler. The parenthetical CLI mapping is slightly incidental but cheap and useful for traceability.

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, it covers action, prerequisites, refusal semantics and required credentials — enough for an agent to call it or back off correctly. Only the outcome/response of a successful deletion is left unstated.

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 schema already documents that name comes from list_registry_projects, so the description adds essentially no parameter meaning. Baseline 3 is appropriate since the schema carries the load.

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 (delete a project in the Ankra registry) and immediately narrows scope with 'extra project', distinguishing it from the org's own project and implicitly from delete_project/create_registry_project siblings. The CLI twin reference adds precision about which surface this maps to.

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 concrete preconditions that select or block this tool: the project must be empty of repositories, unreachable by robots, and not the organisation's own project, plus a credentials.delete requirement. It does not name an alternative tool, but the refusal conditions effectively tell the agent when not to call it.

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