create_release

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

Annotations provide readOnlyHint=false, idempotentHint=false, destructiveHint=false, which are relatively uninformative. The description adds meaningful behavioral context: the release body is sent via stdin, is not written to the audit log, and the tool only creates drafts. This goes well beyond the annotations and surfaces important privacy and side-effect information the agent wouldn't otherwise know.

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, each earning its place: purpose, constraint, and behavioral nuance. Zero wasted words, information-dense, and front-loaded with the core action first.

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 9-parameter tool with no output schema and low schema coverage, the description handles the critical behavioral distinction (draft-only, stdin body, audit-log exemption) well. But it omits guidance on when a release vs a tag is appropriate, or what fields are typically required beyond the 3 mandatory ones. Slightly above baseline given the unusual stdin/audit behavior is disclosed, but leaves some parameter-combination questions unanswered.

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 only 33%, so the description carries responsibility for clarifying parameters. The description explains the 'body' parameter's transport mechanism (stdin) and its audit implications, which adds value beyond the schema. However, it doesn't clarify the semantic differences among the 9 parameters (e.g., targetCommitish vs tagName, prerelease vs generateReleaseNotes), leaving ambiguity for several undocumented params. It compensates partially but not fully given the low coverage.

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 specific verb+resource ('Create a draft release in an allowed repository'). Clearly distinguishes from sibling update_release by explicitly noting it cannot publish, and from other repo tools by scoping to releases. The 'draft' qualifier plus 'cannot publish' disambiguates well.

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 a limitation ('This tool cannot publish a release') and a constraint ('in an allowed repository'), which tells the agent when NOT to use it. However, it doesn't explicitly name update_release as the alternative for publishing or editing, leaving some ambiguity about when to use the sibling. Clear context but no formal exclusions naming specific siblings.

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