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

Goes far beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing the consequential traits: the password is returned ONCE and stored only as a hash, so it must be saved immediately; a dedicated least-privilege `porkbun-agent` editor user is created on first use; administrator grants arbitrary code execution and requires acknowledge_full_access; rate limit of 20 mints per account per hour; revocation via delete_wp_credentials.

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 audience and the no-credential alternatives before the mechanics, and nearly every sentence carries a distinct operational fact. It is a dense single paragraph of run-on sentences, though, so scannability suffers slightly for a definition this information-heavy.

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 credential-minting mutation with no output schema, it covers everything an agent needs: return-value handling (save the password once), prerequisites and eligibility exclusions, privilege escalation guardrails, revocation path, and rate limits. Nothing material is left to inference.

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; the description still adds meaning beyond the schema by explaining the default identity and privilege model (a dedicated `porkbun-agent` user with the editor role, created on first use) and the security consequence of the administrator enum value. It does not add detail for `name` or `dry_run`, but those are adequately self-documenting in 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?

States a specific verb and resource: mints a WordPress Application Password for a Cloud for WordPress site, usable over the WP REST API via HTTP Basic auth. It immediately distinguishes itself from the sibling path (wordpress_request / wordpress_upload_media) by audience — agents making their own HTTP requests — so an agent can choose without opening schemas.

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-to-use (scripts / Claude Code making raw HTTP calls), explicit when-not-to (use wordpress_request and wordpress_upload_media, which need no credentials), and a hard gating rule for the administrator role ('only request it if the user explicitly asked for admin-level access'). Prerequisites are named: site must be provisioned and ACTIVE, poll get_hosting, free $0 preview sites excluded.

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