find_comments

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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), it discloses the two-stage matching process, case-insensitive phrase matching with an all-words fallback, exclusion of workflow-bot nags and service stamps, and newest-first ordering. These behavioral details help the agent predict exactly what results will be returned and how the matching is performed.

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 front-loaded with the core purpose and the user-facing question it answers, then compactly explains the two-stage algorithm, filters, and ordering. Every sentence earns its place—there is no filler or redundant restatement of the tool name. The Args list is clear and scannable.

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 read-only search tool with an output schema, the description covers everything needed to call it correctly: matching mechanics, optional filters, ignored content, and result ordering. It doesn't need to describe return values because an output schema exists, and no critical behavioral or use-case information is missing.

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 per-property descriptions and only titles/defaults, so schema description coverage is 0%. The description's Args block compensates fully: it explains each parameter, highlights that 'text' is required, clarifies that 'author' adds a commenter filter, notes 'project' limits to a project key, gives the default for 'max_results', and marks 'instance' as optional. This adds substantial meaning beyond the bare schema.

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 description states a clear verb+resource: 'Find issues by what their COMMENTS say,' and gives the concrete use case 'the ticket where someone wrote …'. It clearly differentiates from broader search tools like search_issues by focusing on comment text, and from comment-mutating siblings (add_comment, update_comment, delete_comment) by being a read-only find operation.

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 provides a clear use case and defines when to use it: any time you need to locate tickets based on comment content. It also offers detailed guidance on how the search works (full-text query with optional commenter filter, local matching, fallback behavior). However, it does not explicitly name the sibling tool to choose when searching issue fields (e.g., search_issues) or state exclusions, leaving some to inference.

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