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

Annotations already cover the read-only and closed-world profile, and the description adds material context beyond them: failure cases (site never read, draft, answers not found), the remediation path (clickd_rescan reads it), and the auth requirement ('Works with no key'). That is precisely the extra behavioral layer annotations cannot express.

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 When/Instead/Inputs/Returns/Fails in a predictable labelled order, with zero filler. The telegraphic phrasing ('Fails: a site never read, or a draft, answers not found') is slightly compressed to the point of ambiguity, which keeps it just short of top marks.

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 return-value disclosure itself and does so for both formats. Combined with inputs, failure modes, remediation and sibling routing, an agent has everything needed to call this correctly on the first attempt.

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 goes further by defining what each format value actually yields: markdown returns the whole list as Markdown text, steps returns the four highest-value fixes with pages, points and a hand-off prompt. This adds selection meaning beyond the bare enum values.

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 ('Gets a site's fixes as a work order') and enumerates the content: what to fix, order, how, why, which pages. That framing makes it clearly distinct from clickd_site (score) and clickd_todo (single next fix), which the description names explicitly.

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 ties invocation to the start of site work and to a completed read signalled by clickd_changes. The 'Instead' clause names two alternative siblings and the condition that selects each, so routing is unambiguous.

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