stale_work_audit

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

The description upfront declares the tool is a '[READ]' operation, indicating no mutation. It explains that it 'flags' issues and returns a dictionary with specific keys like count and thresholds. Since no annotations are provided, this description adequately discloses the tool's behavior and what the output contains.

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 concise yet comprehensive, front-loading the purpose and then detailing parameters and return format. Every sentence serves a purpose, and the structure with paragraphs and bullet-like lists makes it easy to scan. No unnecessary 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?

For a complex audit tool with 8 parameters and no output schema, the description covers the input, logic, and output thoroughly. It explains the relationship between injected vs live data. Minor omissions like error handling or performance notes do not detract significantly from overall completeness.

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?

With 0% schema coverage, the description does heavy lifting. It explains each parameter's purpose, defaults (e.g., stale_mr_days=14), and how injected rows should be structured (fields like id, title, updatedAt, draft). The 'target' parameter is only briefly described, but overall the description adds significant meaning beyond the raw schema.

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 begins with '[READ] Long-open MRs/PRs, inactive branches, protection config gaps.' which clearly states the tool's function as an audit. It details what it flags (stale merge requests, inactive branches, protection gaps), distinguishing itself from sibling list tools by performing analysis rather than simple retrieval.

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 explicitly explains two usage modes: 'Pass injected rows for pure analysis, or a project to pull live.' It emphasizes that project is required unless rows are injected, providing clear context for when to use each parameter. However, it does not explicitly state when not to use this tool or compare it to alternatives.

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