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

Goes well past the annotations: discloses the auth requirement ('Needs a person's key'), the cross-account failure mode ('a proposal or task not the person's keeps nothing and says so'), the return fields, and a privacy constraint ('Never send private data'). Annotations only say it is a non-destructive write with openWorld=false; the description supplies the why-and-what-happens instead.

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?

Labeled sections (When, Instead, Inputs, Returns, Fails) with the primary action front-loaded; every line carries distinct information and there is no filler or repetition of the title.

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 an 8-parameter write tool with no output schema, the description still covers trigger timing, alternatives, the meaning of each non-obvious parameter, the return shape, the failure case, and the auth prerequisite. Nothing an agent needs to call it correctly is missing.

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 the baseline is 3, but the description adds cross-tool semantics the schema lacks: `proposal` names the proposal carried out (pointer to clickd_propose) and `task` the queued task finished, plus the comma-separated convention for `files` and `rules`. It does not restate the enum values in full, which the schema already covers.

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?

Specific verb+resource: 'Records a step of work on a site', immediately narrowed to 'what you planned, changed or checked, or where you got stuck'. That framing plus the named siblings (clickd_propose, clickd_todo) makes it unmistakable against the rest of the clickd family.

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?

An explicit 'When:' clause (after each step, including steps that carry out a proposal or queued task) and an explicit 'Instead:' clause routing to clickd_propose for deploy approval and clickd_todo for waiting tasks. When-to-use, when-to-use-something-else, and the alternatives are all named.

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