github_watch

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

No annotations are provided, so the description must fully disclose behavior. It mentions cost and output format, but fails to clarify key traits: whether this is a one-time query or persistent watch, whether it requires authentication, or if it has side effects. The term 'watch' could imply ongoing monitoring, which is ambiguous.

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 (three sentences) and front-loaded with purpose, then output, then cost. Every sentence adds value with no redundancy.

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 description covers purpose, output, and cost, but lacks details like whether the watch is persistent, the anomaly score range, or authentication requirements. For a tool with no output schema and no annotations, it is moderately complete but has gaps.

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?

The schema covers 100% of parameters with clear description ('GitHub repo in owner/repo format'), so the description adds no new parameter meaning. Baseline score of 3 is appropriate.

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 the tool's purpose: watching a GitHub repo's activity stream for anomalous development patterns. It lists specific examples (commit bursts, force pushes, etc.) and describes the output (story label and anomaly score), making it distinct from sibling tools like repo_scan or anomaly_scan.

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 usage for anomaly detection in GitHub repos, but lacks explicit guidance on when to use this tool vs siblings (e.g., anomaly_scan). It does not mention prerequisites, when not to use it, or alternatives, leaving the agent to infer from context.

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