bulk_read_issues

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

With no annotations, the description carries the behavioral burden. It discloses that bodies and comments are omitted, that it is lightweight, and that the return includes count, error_count, issues, and errors, which reveals partial-failure behavior. This goes beyond a bare 'read issues' statement, though it does not mention authentication or rate-limit implications.

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?

The description is compact and well-structured: purpose, a one-sentence caveat, an Args line, and a Returns line. Key information is front-loaded, and every sentence contributes to selecting or invoking the tool correctly.

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 bulk read tool with no annotations and no output schema, the description covers the purpose, the key alternative, the state argument, and the return shape. However, the near-total lack of parameter semantics for the required issue_numbers parameter leaves a gap that makes the description less complete than it should be for a tool of this complexity.

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?

The input schema has no parameter descriptions and does not even list 'issue_numbers' in properties, leaving necessary semantics undocumented. The description only explains 'state' and its allowed values; the required parameters owner, repo, and especially issue_numbers are left to inference. Since schema coverage is near zero, the description should compensate for at least the main input, but it does not specify the expected format for issue_numbers.

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 sentence states a specific verb ('Read'), a specific resource ('issues'), and the scope ('many issues at once'), and it enumerates the exact summary fields returned. The phrasing clearly distinguishes it from read_card, which is the sibling for full content, so an agent knows what this tool is for without ambiguity.

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?

The description explicitly says 'Use read_card for full content', naming the alternative and the condition for choosing it instead. It also explains the state filter and its default, giving clear guidance on when to use this tool to filter results versus reading individual issue details elsewhere.

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