Propose Search Console changes (applies nothing)

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true; the description adds substantial context beyond that — proposals are stored, add_site leaves the property unverified, delete_sitemap doesn't stop crawling, remove_site can't be recovered by undo, and indexing can't be requested. The only gap is that it doesn't say where the proposal is stored or how long it lives, and the ⚠ mechanism is referenced without a full definition. No contradiction with annotations (destructiveHint=false is consistent with 'applies nothing').

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 the key fact ('nothing is changed') and the approval workflow before the supported-types list. The long parentheticals in the second sentence make it denser than necessary, but every clause carries real information.

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 tool with a single, deeply structured parameter and no output schema, the description covers prerequisites (user verification for add_site), irreversibility (remove_site), impossible operations (indexing requests), and the stale-connection edge case. An agent has what it needs to call this correctly and to instruct the user afterward.

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% with per-variant descriptions, so the baseline is 3; the description still earns credit by enumerating the four supported change types and adding operational nuance (submit_sitemap resubmits, add_site may stay unverified) that helps an agent pick the right `type` value. It does not mention the maxItems of 20 or explain what the ⚠ line looks like in the payload.

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 ('checks Search Console changes against the live property and stores them as a proposal') and immediately disambiguates scope with 'nothing is changed'. The title and first sentence make clear this is a dry-run/staging tool distinct from apply_changes and the other propose_* siblings.

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?

Gives an explicit workflow: show the summary to the user, apply only after approval with apply_changes, and use undo_changes to reverse (with the ⚠ exception named). It also names apply_changes and undo_changes as the alternatives, 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.