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

Goes well beyond the annotations: it explains that reverting is instant because publishing only controlled visibility in the public manifest and never touched the audited site's origin content, flags it as a MUTATION, notes it is FREE with no credit cost, and states the org-admin requirement. That clarifies why destructiveHint=false even though this is a write operation — exactly the context an agent needs before invoking.

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 tight sentences, front-loaded with the effect and then the cost/auth facts. The leading 'Patches:' namespace label and the long em-dash parenthetical are marginally wasteful but carry real meaning about instant/non-destructive behavior.

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 two-parameter mutation with no output schema and full schema coverage, the description supplies everything material: effect, reversibility semantics, cost, and permission requirement. Nothing an agent needs to call 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 description coverage is 100%, and both patchId and projectId are documented in the schema with provenance pointers (list_patches, list_projects). The description adds nothing about the parameters, so the baseline of 3 applies.

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: 'stops serving a published fix' for patches, which is precise about the effect rather than just restating the name. It does not name the sibling it undoes (publish_patch) or distinguish itself from draft_patch/batch_draft_patches by name, so an agent gets the concept but not the routing.

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?

Usage context is implied — undo a published fix — and it states a prerequisite (org admin) and cost (FREE). It never says when to use this instead of publish_patch or the auto-publish disable tools, and offers no when-not guidance.

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