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

Annotations only declare readOnlyHint=false/destructiveHint=false, so the description carries most of the load and delivers richly: default read-only vs push-scope behavior, 2h default/master 24h max lifetime, required access level (owner/collaborator/team/org, public read insufficient), 'repo' scope, audit logging, and the fact that the token is returned once. This is exactly the mutation context an agent 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 purpose followed by scope/auth/expiry/return details, and every clause adds operational value. It is dense and multi-clause but not padded; a touch long, keeping it just under the top mark.

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 token-minting mutation with no output schema, the description enumerates the return shape ({id, title, readOnly, expiresAt, token, cloneUrl, url}) and covers permissions, scope, expiry, and audit behavior — everything needed to invoke it correctly and safely.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it clarifies that read_only:false is only granted if you have write access and that expiry defaults to 2h with a 24h cap. That reinforces rather than merely restates the field docs.

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 ('Mint a short-lived, repository-scoped HTTPS clone credential (a deploy token)') and adds the return artifact ('ready clone URL'). This clearly distinguishes it from adjacent siblings like create_repo_token, clone_url, and create_runner_registration_token.

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 the selecting context — 'for a sandbox or CI box that has no PAT' — which tells the agent when this is the right tool. It does not explicitly name exclusion conditions against the sibling token tools, but the use case is concrete enough to route correctly.

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