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

Beyond the annotations it discloses quota consumption ("Uses one of the organization's monthly drafts per page"), a concrete mutation-safety guarantee ("A draft changes nothing on the website"), an optimistic-concurrency behavior on stale evidence, and a human-confirmation gate. These are exactly the operational facts an agent needs before invoking a non-idempotent, non-read-only tool, and they reconcile rather than contradict the destructiveHint=true annotation.

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 key facts — fix types, quota cost, no-op behavior, precondition, and confirmation gate — are front-loaded and each sentence carries information. Some sentences are run-on ("Drafts the fix for a finding where Website Growth Ops can: ..."), which slightly hurts scannability.

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 three-parameter mutation tool with no output schema, the description covers the workflow error path, the quota side effect, the human-in-the-loop handoff to tc_confirm, and the safety guarantee. The only real omission is the meaning of the domain parameter, which does not block correct invocation given the finding_id provenance.

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 description coverage is 0%, so the description must carry parameter meaning, and it only partly does: it explains the provenance of evidence_id and implies finding_id, but never explains the required domain parameter or that these must match the website the finding belongs to. The regex formats and constraints are left entirely to the schema.

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 opens with a specific verb and resource ("Drafts the fix for a finding") and immediately enumerates the concrete fix kinds it produces: page titles, meta descriptions (fact-checked), or internal links. It is clearly distinguishable from siblings such as webops_finding (which supplies the finding) and webops_accept/webops_reject.

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?

It states the prerequisite source ("The finding and its evidence_id come from webops_finding"), the failure branch (stale evidence records nothing and tells the caller to re-read the finding), and the follow-up path ("returns a summary and a code for tc_confirm"). An agent can place this tool correctly in the workflow without inference.

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