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

Annotations only flag destructiveHint=true; the description goes further by naming the actual destructive consequence — an already-live page begins retiring because a draft cannot be served — and the queue state of the topic. That is substantive context beyond the structured hints. It stops short of covering reversibility of the requested rewrite or the note's effect on scope.

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?

Three short clauses, front-loaded with the action, and each remaining sentence earns its place by disclosing a real side effect (queue retention, live-page retirement). No filler or restatement 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 a two-parameter mutation with a descriptive schema and destructive annotation, the description supplies the key operational fact an agent would otherwise miss: the live page gets retired. What it leaves out is comparative routing against sibling lifecycle tools and whether the regenerated draft replaces or forks the existing page.

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% and both parameters are described there, so the baseline is 3. The description's 'carrying a note on what to change' only paraphrases the note field's own description and adds no format, length, or scope nuance. It does not compensate for anything the schema lacks, because the schema lacks nothing.

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 concrete verb+resource pair: 'Send a hosted page back to be written again, carrying a note on what to change.' Clear enough to act on without opening the schema. It does not name the nearby siblings (reject-hosted-page, retire-hosted-page, dispose-hosted-claim), so the differentiation burden is left implicit even though the verbs differ.

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?

Usage is only implied: the page needs a rewrite, so request it. There is no explicit 'use this instead of reject-hosted-page when...' guidance despite several adjacent lifecycle tools. The stated collateral-effect (live page retiring) helps an agent judge consequences but does not route selection between alternatives.

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