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

Annotations only provide the destructive/readOnly flags; the description goes well beyond them by enumerating exactly what is destroyed (git data, LFS, issues, PRs, releases, packages, CI history, settings), noting backups age out on schedule, and disclosing the audit event repo.purge. This is precisely the contextual depth a destructive tool needs.

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-loaded with the two most important facts (PERMANENTLY, IRREVERSIBLE) in caps, then consequences, preconditions, auth, audit, and return shape in a tight sequence. Dense but every clause carries decision-relevant information for a destructive action.

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?

Despite no output schema, the description supplies the return shape ({purged: true, id, full_name}), the auth scope, the audit event, and the preconditions. Nothing an agent needs to safely invoke this irreversible tool 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%, so the baseline is 3. The description adds workflow meaning by tying `confirm` to a deliberate confirmation guard ('must be its full name (owner/name)') and clarifying that `id` refers to the deleted repository's id, making the pairing's intent explicit rather than merely restating types.

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 ('PERMANENTLY delete an already-deleted repository') and immediately distinguishes the action from waiting out the restore window. The reference to gluecron_delete_repo and the restore-window concept clearly separates it from sibling tools like gluecron_restore_repo and gluecron_delete_repo.

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 states the when ('now, instead of waiting for its restore window to end') and the hard precondition ('Only works on a repository already deleted with gluecron_delete_repo'). It also states the auth requirement (owner or site admin, 'admin' scope), so the agent knows exactly when this tool is callable.

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