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

Annotations already indicate read-only and non-destructive behavior. The description adds valuable context beyond annotations: it warns that results may be truncated on large corpora and directs the agent to inspect metadata.candidate_retrieval and metadata.truncated before treating broad results as exhaustive. It also discloses that results include project_kind and collection_metadata, which is helpful given there is no output schema.

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 three sentences, with the purpose front-loaded in the first sentence. Each sentence earns its place: the first states the search facets, the second notes important result fields, and the third gives a crucial caveat about truncation. No filler or redundant content.

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 search tool with 10 parameters and no output schema, the description covers the core aspects: search dimensions, key result fields, and a warning about metadata for truncation. It does not mention pagination or ranking options, but these are described in the input schema. The caveat about large corpora adds needed context for correct use of results, making the description reasonably complete.

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 40%, so the description must compensate. It lists the key filter dimensions (query, category, deployment, difficulty, language, Cloudflare readiness), mapping to several parameters and clarifying their role as search criteria. However, it does not add detailed semantics for parameters like cursor, limit, ranking, or require_d1, which rely on schema descriptions. The description partially compensates for the coverage gap but stops short of fully explaining parameter usage.

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 leads with a specific verb ('Search') and resource ('Git.Top projects'), then lists the exact filter dimensions (query, category, deployment, difficulty, language, Cloudflare readiness). This clearly distinguishes it from sibling tools like compare_projects, get_project, and recommend_project, which have different verbs and purposes.

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 does not explicitly state when to use this tool versus alternatives like get_project (for a specific project) or recommend_project. It provides a caution about inspecting metadata for truncation, which is useful for interpreting results, but it does not guide tool selection among the siblings.

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