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

Annotations only declare readOnlyHint=false and destructiveHint=false, but the description adds substantial behavior: non-posting conditions (unpaid, missing DATABASE_URL, stop, timeout), the stop-on-missing-webhook case, the approval-gated write flow, and the $49 Action Gate seat requirement. This is exactly the extra context annotations cannot convey.

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?

Front-loads the gate identity and keeps every sentence informational, with no filler. The clipped, telegraphic phrasing ('Unpaid, missing DATABASE_URL, stop, and timeout do not post') is dense but readable and purposeful.

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 and no required parameters, the description covers the failure modes, approval loop, and prerequisites an agent needs. It names the decision states (go/wait/stop) but does not describe the response shape on success, a minor gap given there is no output schema.

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 every parameter is already documented in the schema, including approval_id's provenance and payload/preview meaning. The description reinforces the approval_id re-call flow but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 action (validate preview, run check_action gate, POST approved preview to the CRM webhook) on a specific resource. It also names the sibling tools it interacts with (check_action, get_approval), so an agent can distinguish it from email.send/slack.post. It does not explicitly contrast itself with those other write-delivery siblings, keeping it just short of a 5.

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?

Gives clear operative conditions: it posts only when decision is go, and if decision is wait it must poll get_approval and call crm.write again with approval_id. It does not state when to prefer crm.write over sibling channels like email.send or slack.post, so it falls short of explicit alternatives guidance.

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