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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful behavior beyond that: results are capped at five and matching is "judged by shared GitHub topics," which tells the agent how alternatives are chosen. It says nothing about what happens when the repo is unknown or how confidence is expressed.

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?

A single sentence that front-loads the triggering condition before the output description, with no filler. The parenthetical and the "whether it does" clause make it read awkwardly, costing a point on clarity.

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?

With no output schema, the description must convey return values, and it does in outline: a run/no-run verdict plus up to five topic-matched repos. For a two-parameter read-only lookup that is close to sufficient, though edge-case behavior (no matches, ambiguous repo reference) goes unmentioned.

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 50%: repo is documented in-schema, but os is only an enum (mac/windows/linux) with no explanation. The description adds no parameter detail at all, so it neither compensates for the gap nor clarifies that os means the user's system rather than a target platform. Baseline 4 applies since the schema carries the repo format.

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?

"Find alternatives" plus "whether it does [run], and up to five similar repos that do" names a concrete verb and the two-part output, which separates it from search_repos and the setup-manual siblings. The phrasing is slightly tangled ("whether it does") but the intent survives.

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 trigger is explicit and conditional: "When a repo doesn't run (or only partly runs) on the user's system." That tells the agent when to reach for this instead of a plain repo search. No exclusion or explicit sibling hand-off is given, which keeps it short of a 5.

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