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

With readOnlyHint and openWorldHint already declaring the safety profile, the description adds genuinely new operational context: a cost of 1 credit and a 30-item page limit, plus the constraint that only public repositories are returned. It stops short of describing rate limiting or error behavior, but the additions are substantive.

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 fragments, front-loaded with the resource identity and ending with the key input constraint. Nothing is wasted, though the telegraphic style leaves out connective meaning that would cost only a few more words.

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?

Pagination (30 per page) and cost are covered, which matters given there is no output schema. However, for a 7-parameter tool with 43% schema coverage, the description leaves sorting, filtering by type, and the structure of returned repository data entirely unexplained.

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 coverage is only 43%, so the description needs to carry weight. It clarifies the handle/url mutual exclusivity (a useful addition), but four parameters — sort, type, direction, and cache_max_age — are undocumented in both schema and description, and 'type' in particular is easy to misread against the phrase 'owned by'.

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 names the resource and its scope precisely: public repositories owned by a user or organisation, with a page size. The listing verb is only implied by '30 per page', but an agent can still distinguish this from github_repository (single repo) or github_trendingRepositories (global trending).

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 only routing guidance is 'Pass either `handle` or `url`', which is input mechanics rather than when-to-use. It never says when to prefer this over github_repository, github_activity, or github_contributions, so an agent must infer the choice of sibling from names alone.

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