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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description goes far beyond by disclosing soft-delete semantics (immediate disappearance from git/web/REST/MCP/CI/webhooks/search, reserved name, 90-day restorable_until window), side effects (CI cancellation, webhook delivery stop), permission model, required token scope, audit event name, owner notification, and the exact return shape. This is exactly the extra context destructive operations need.

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?

Content-dense with essentially no filler — every clause adds a fact an agent needs (soft vs hard, restore path, permissions, scope, return value). It is front-loaded with the most decision-relevant fact (soft delete). It loses a point for being a single very long run-on passage, which makes the permission/scope details harder to scan than a short bulleted structure would.

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?

There is no output schema, so the description supplies the return contract itself ({deleted, soft, id, restorable_until}) plus the restore deadline. Combined with permissions, scopes, and side effects, nothing material is missing for a destructive, non-idempotent tool with no structured return metadata.

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% — both 'repo' and 'owner' are documented in the schema itself. The description only adds ownership context ('the personal owner, or an org owner for an org repository') which is about authorization rather than argument format, so the schema still carries the parameter burden. Baseline 3 is appropriate.

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 (delete) and resource (repository) and immediately qualifies it as a SOFT delete, which is the key distinction from the other deletion-flavored siblings (gluecron_purge_repo). An agent can tell exactly what happens and how it differs from purge without opening either 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 routes the agent to alternatives and conditions: use gluecron_restore_repo to undo within the window, use gluecron_purge_repo to remove permanently before the window expires. It also states the authorization precondition (repository owner or site admin; admin collaborators and org admins refused) and the required 'admin' token scope, which is the deciding factor for whether the call will succeed.

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