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

With readOnly/idempotent/destructive/openWorld annotations already covering safety, the description adds non-obvious pagination behavior: search applies per page and an empty page can still carry a next cursor. It does not cover auth or rate limits, but that is minor given the annotation set.

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, front-loaded sentences with no filler. The pagination edge case is valuable, though the first sentence's 'find a GitHub repository' (singular) is slightly loose for a list tool.

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?

Output schema exists, so return values need no explanation; annotations cover safety; schema documents parameters. The description adds purpose and pagination edge-case context, though it stops short of mapping the tool against get_repository/list_workspaces.

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 limit, cursor, search, and workspaceId are fully documented in the schema. The description adds only that search is page-scoped, which slightly clarifies behavior but does not add syntax or format detail beyond the 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?

States the resource (GitHub repository in Runzumi) and two purposes (find a repository, check runner readiness), plus paginated search via 'The search applies to each page.' However, it does not explicitly differentiate from the sibling get_repository or say it lists repositories, leaving the list-vs-get boundary to the name/title.

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 opening 'Use this to...' gives clear intended context (finding repos and checking runner readiness). It does not name alternatives or when not to use it (e.g., use get_repository for a known repository), so no exclusions.

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