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

Beyond the annotations (which only flag it as non-read-only and non-idempotent), it discloses the data-handling rule (no page content, personal data, or credentials) and the acceptance boundary for detours. It doesn't state that reports are shared/persisted for other agents beyond a brief 'so the next agent knows'.

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?

Three front-loaded sentences: purpose, privacy constraint, then detour rule. No filler, and the constraint ordering matches how an agent would reason about what to submit.

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 7-parameter write tool with a nested object and no output schema, it covers purpose, safety, and the trickiest decision (detour legitimacy). The omission of three optional telemetry fields is minor since the schema documents them.

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 57%. The description adds meaningful guidance on the detour object (what counts as legitimate) but says nothing about action, framework, latency_ms, or http_status, and leaves the outcome enum values to the 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?

States a specific verb and resource: 'report the outcome' after acting, so the next agent benefits. It implicitly contrasts with siblings like check_road (pre-action) and watch_road, though it never names them explicitly.

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?

Timing is clear ('After acting'), and it specifies when to include a detour and what kinds are acceptable. It does not explicitly route to or away from sibling tools by name, 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.