search_repositories

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

With no annotations provided, the description carries the full burden of disclosing behavior. It does not say whether authentication is required, whether results are scoped to a user, how pagination behaves, what the default sort/order values mean operationally, or what response shape to expect beyond the schema. The only behavioral hint is that GitHub search qualifiers are supported, which adds some context but leaves most runtime behavior undocumented.

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 two short, front-loaded sentences with no filler. It efficiently communicates the core purpose and one key capability. It could have used the space to define parameter semantics, but as far as conciseness for the current content, it is well structured.

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?

The tool has five parameters, no annotations, and an output schema, but the description covers only the query concept. It omits guidance about how language, sorting, ordering, and pagination interact, how qualifiers are used in practice, and what kinds of queries are appropriate. The presence of an output schema covers return shapes, but input behavior remains under-specified for correct invocations.

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 0%, so the description must compensate, but it only explains that 'query' is a search query supporting qualifiers. It does not define the meaning or allowed values for sort, order, language, and per_page, even though these parameters have defaults in the schema. This is only a minimal add beyond the structured types.

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 a specific verb ('Search'), a resource ('GitHub repositories'), and the distinguishing mechanism ('by query'). It is distinct from siblings like get_repository or list_user_repos, which are about fetching known repos or listing a user's repos rather than searching across all repositories.

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 implies the tool is for query-based repository search and mentions GitHub search qualifiers, which suggests when to use it over simpler listing/getting tools. However, it does not explicitly state when not to use it or contrast it with alternatives such as list_user_repos and get_repository, leaving the agent to infer the decision boundary.

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