Remove an extra share link

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

Annotations only declare destructiveHint/readOnlyHint/idempotentHint; the description goes beyond them with the actual consequence set: "Its page says the link was turned off; the build and its other links keep working. This cannot be undone." It also discloses the consent requirement and the developer-role gate, which annotations cannot express.

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 short sentences, front-loaded with what is destroyed, then the blast radius, then the safety requirement and role. No redundant restatement of the title or name.

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 destructive two-parameter tool with no output schema, everything an agent needs is present: the identifier source, the irreversibility, the unaffected resources, the confirmation protocol, and the required role.

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 50%; the description compensates by telling the agent where the `link` slug comes from (list_build_links) and that `confirm` must be passed as true after asking the person. The `const: true` in the schema already constrains `confirm`, so the added meaning is real but modest.

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?

"Turn off one extra share link (by its slug from list_build_links)" gives a precise verb, a bounded resource (one extra link, not the build or its other links), and the identifier source, which cleanly separates it from add_build_link and share_build_with_testers.

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?

It states the prerequisite identifier (slug from list_build_links), the required confirmation flow ("Ask the person first and pass confirm: true"), and the permission level ("Developer role"). It does not name an exclusion or a case where a different tool should be used instead, so it stops short of a 5.

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