Get issue

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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower, and the description still adds real context: the cached-vs-generated distinction ('Never starts a new explanation') is a genuine side-effect boundary, and 'privacy-safe evidence' tells the agent what class of data comes back. It stops short of describing pagination or size limits.

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 the mutation-safety fact and the single-resource scope, then the payload list. It is one dense paragraph with no filler sentences, though the mid-sentence enumeration of evidence types is long enough to slightly dilute the key routing information.

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?

With no output schema, the description carries the return-value burden and does so by listing the returned fields, including the AI explanation's sub-parts. Annotations cover the safety profile. It is nearly complete, missing only volume/shape caveats (pagination, evidence truncation).

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 the single 'id' parameter already documents the ref format including r123/f456. The description's 'Also accepts finding ids' restates that schema detail rather than adding new syntax or constraints, so the baseline 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?

The first clause names a specific verb and resource ('Read-only. One issue') and then enumerates the payload: occurrences, users, releases, evidence, fix PR, cached AI explanation. This clearly separates it from list_issues and get_finding, and the 'Also accepts finding ids (r123, f456)' note pins down its scope relative to the finding siblings.

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 gives an important when-not ('Never starts a new explanation'), which prevents an agent from expecting generation on this call. However it never explicitly routes the agent to alternatives (e.g. get_finding for a finding-centric read, or why to pick this over that) despite overlapping id acceptance with get_finding, leaving the sibling choice to inference.

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