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

The description substantially exceeds the annotations. It discloses state transitions (root flips to `integrated`), the trail-note posting, actor stamping as source api:key:<id> (never as a human), and rich idempotency semantics — replaying the SAME deploy_id returns the same completion with replayed:true, while a DIFFERENT deploy_id after integration is refused (409) without mutation. It also covers auth (agent:dispatch) and invalid-input handling (bad_deploy_id). This is exemplary behavioral disclosure with no contradiction against annotations.

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 information-dense and logically ordered (purpose, prerequisites, behavior, idempotency, fallback), but it is verbose and carries jargon ('D4:', 'protocol v0.2, migration 181, coord_record_integration', 'stop landing on Mike') that adds narrative noise without helping an agent select or invoke the tool. The core facts could be delivered in about half the 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 mutation tool with no output schema, the description is unusually complete: prerequisites, valid input format, state change, actor stamping, idempotency behavior, failure modes (409, bad_deploy_id), auth requirement, and the human fallback are all covered. The only gap is the exact shape of the returned completion, but that is mitigated by hints like 'returns the same completion (replayed:true)'.

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%, so baseline is 3. The description mirrors the schema's deploy_id format (24 lowercase hex, optional 'deployed:' prefix, optional build-ref hex) and adds validation context ('Deploy' and anything else is refused, bad_deploy_id) and the idempotency coupling to deploy_id. It adds modest value but largely restates what the schema already documents, so it does not push meaningfully above baseline.

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 states a clear verb+resource+outcome: records the Netlify deploy id for an authorized cycle, moving the root from `authorized` to `integrated`. This is unambiguous and distinct from the many tascan_* siblings — it is specifically the integration-recording tool, not a generic task completion tool.

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 spells out concrete prerequisites: root must be `authorized` (checkpoint Approved) with an open Integrate task, deploy_id must be a real Netlify deploy id, and it requires agent:dispatch permission. It also contrasts the agent action with the human ops fallback (completing the card on the worker page), clarifying when the tool is the right path. It does not name specific sibling tools, but the context is well-scoped.

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