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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the auth requirement, the return shape (watch id plus signing secret), and critically that the secret is 'shown once' and used to verify the LaneRouter-Signature header — operationally important, irreversible-to-recover information. It does not explain repeat-call behavior on an already-watched target, which is the main remaining gap given the non-idempotent hint.

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 tight sentences, front-loaded with the outcome, then the prerequisite, then the return contract. Every clause carries information an agent needs; nothing is padding.

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 non-idempotent write tool with no output schema, the description covers the essentials: what it produces, the credential needed, and the one-time secret that governs downstream signature verification. Only the lifecycle counterpart (unwatch_road / duplicate-watch handling) is left unstated.

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%, so the schema already defines target, url, and action; the description adds little beyond echoing that a road is watched and a webhook is signed. The optional 'action' filter is not mentioned at all in the description, so no extra meaning is layered on top of the structured fields.

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 gives a specific verb and outcome — 'Get a signed webhook when a road changes light (green, amber, red)' — which clearly frames this as creating a persistent change subscription rather than a one-off query. It implicitly separates itself from check_road and list_watches, but never names a sibling, so the differentiation is left to inference.

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?

Usage is only implied: the tool is for ongoing notification on a watched target, and the auth prerequisite ('Needs a LaneRouter key') is stated. There is no explicit when-to-use versus check_road (one-off status) or unwatch_road (teardown), and no guidance on what to do if a watch already exists on the same target.

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