agent_scan

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

No annotations provided, so description carries full burden. It discloses read-only mode by default, destructive behavior when autoRotate=true (overwrites secrets, may break integrations), and mentions tool policy and return format.

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 concise paragraph that front-loads the main action. Each sentence adds value, though slightly longer than necessary. 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?

No output schema, but description states it returns a JSON report of per-project findings and rotations. Covers all key aspects of behavior, including optional destructive action, for a multi-project tool.

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 100%, baseline 3. The description adds valuable context beyond schema: explains default for projectPaths (server.cwd), and warns about destructive nature of autoRotate. This extra guidance justifies a 4.

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 specifies the tool runs a multi-project health pass gathering decay status, audit anomalies, and manifest gaps, with optional auto-rotation of expired secrets. It distinguishes from siblings by naming health_check, detect_anomalies, and check_project.

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?

Explicitly states when to use this tool as the 'canonical agent maintenance loop' and when to prefer alternatives like health_check (single read-only), detect_anomalies (audit-only), or check_project (single-project manifest check).

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