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

Goes well beyond the annotations: discloses the email/approval workflow, the 72-hour link expiry, that `diff` is 'shown and never applied', the auth requirement ('Needs a person's key'), the 20-per-site-per-hour limit, and the failure mode for an unclaimed site. The only gap is the return payload's `note` and `promise` fields, which are named but not explained.

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-loaded with purpose, then labeled blocks (When/Instead/Inputs/Returns/Fails) that make scanning easy and contain no filler. The telegraphic, fragment-heavy prose costs it a point, since '20 proposals a site an hour at most' takes a moment to parse.

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?

With no output schema, the description carries the return burden and does so ('proposal ({ id, state, deploy, ... }), note and promise'), while also covering auth, rate limits, and failure cases. An agent has everything needed to call this correctly.

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 already 100%, so the baseline is 3, but the description adds meaning the schema lacks: `diff` is never applied, `pages` is comma separated, and `rule` is 'the rule id it answers'. That extra semantic layer justifies moving 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?

States a specific verb and resource ('Proposes a change before you deploy it') plus the mechanism: an email with Approve/Decline links that lapse in 72 hours. That mechanism alone distinguishes it from the sibling clickd_proposals, which merely lists or waits on proposals.

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?

Explicit 'When:' clause (before each deploy to a site clickd_proposals says is set to approve) and an 'Instead:' clause naming two alternatives with the exact conditions that select them (clickd_proposals to wait for the answer, clickd_log_work to record the work once done).

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