search_repositories

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

Annotations include readOnlyHint=true and openWorldHint=true, so the safety profile is already known. The description adds that it is read-only and does not mutate GitLab data, reinforcing but not contradicting annotations. It also discloses that missing resources, invalid identifiers, insufficient permission, and rate limits are returned as errors, which is valuable beyond annotations. It doesn't describe the response format or pagination details, but the output schema is absent. Given the annotations cover read-only nature, the description adds meaningful error-handling context, warranting a 4.

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 moderately concise with three sentences. The first sentence clearly states the purpose, the second adds usage and safety context, and the third covers parameter usage. It is informative without excessive length. Slightly could be trimmed, but it is front-loaded with the core purpose. No redundant wording, though the error disclosure could be considered a bit verbose.

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?

Given the tool has no output schema and only four simple parameters all described in the schema, the description covers the purpose, usage distinction, safety profile, and error behavior. It doesn't cover the structure of the search results, but since there is no output schema and the tool is a discovery search, the description is reasonably complete. The missing explicit exclusions for alternatives is a minor gap, but overall adequate.

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%, so the schema documents all parameters (page, query, search, per_page). The description adds value by explaining the relationship: 'query' is an alias for 'search', and it clarifies that identifiers should be numeric IDs or URL-encoded paths when project_id or group_id are accepted (though those are not parameters in the schema). It also reminds to use required identifiers and pagination fields exactly as documented. This goes beyond the schema's terse descriptions, especially the alias clarification.

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 clearly states the tool searches for GitLab projects with a specific verb (Search) and resource (GitLab projects). It distinguishes itself from siblings by explicitly mentioning 'typed get or list tool when the target identifier is already known', which contrasts with get_project, list_projects, and other typed tools. However, it doesn't name a specific sibling tool that competes for the same search role (such as a hypothetical search_issues), so it doesn't fully differentiate from all 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?

Provides clear guidance: use this for discovery when the target identifier is unknown, and choose a typed get or list tool when the identifier is already known. It also instructs on using project_id/group_id with numeric IDs or URL-encoded paths. However, it doesn't explicitly mention when not to use this tool in favor of specific alternatives like list_projects or get_project, nor does it address pagination when to use page/per_page beyond noting they exist.

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