github_audit_stars_health

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

With no annotations, the description carries the full burden. It discloses that it detects dead abandonware, stale projects, and unmaintained dependencies and provides a composite 0-100 score, which is behavioral. However, it does not disclose side effects (likely read-only), caching behavior, API usage, rate limits, or whether it modifies anything. The refresh parameter hints at live API calls but is not explained in the description. This is a partial disclosure, leaving gaps in behavioral expectations.

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 sentences long, with the primary purpose front-loaded in the first sentence and supporting details in the second. Every phrase adds value, with no redundancy or filler. It is concise and 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?

Given the tool's moderate complexity (3 params, no output schema, no annotations), the description covers the main purpose and some behavior but lacks an explanation of the return value or output format. It mentions health scoring but does not specify what the tool returns (e.g., a list of repos with scores, a summary). Also missing are edge cases, limitations, or usage examples. The description is adequate but not fully complete for an agent to anticipate the tool's output.

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%: all three parameters (filter, refresh, min_health_score) have descriptive schema entries. The description adds minimal extra meaning beyond the schema, such as mentioning the health score scale (0-100) which relates to min_health_score, but does not significantly augment parameter understanding. Per rubric, with high schema coverage, baseline is 3, and the description does not exceed that.

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 uses a specific verb 'Audit' and clearly identifies the resource 'starred repositories' with distinct focus areas: health, maintenance freshness, and licensing safety. It also mentions detection of dead abandonware, stale projects, and unmaintained dependencies, which distinguishes it from sibling tools like github_list_starred (simple listing) or github_recommend_stack (recommendations). The purpose is unambiguous.

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 clearly implies when to use this tool: when an audit of starred repos' health, freshness, and licensing is needed. However, it does not explicitly exclude other tools or state when not to use it. It provides clear context (audit health) but lacks explicit exclusions or alternatives, so it does not fully meet the 'explicit when/when-not' bar, but it is close.

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