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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description goes well beyond them: revisions are destroyed, media survives in the library, block rows persist, and pages with children survive until children are moved. This is exactly the cascade detail an agent needs before an irreversible action.

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?

Dense and front-loaded — the irreversible nature and cascade effects land in the first two clauses. The opening fragment ("On one site of the account, named in site.") is grammatically awkward but costs only a few words.

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 destructive tool with no output schema, the definition covers permissions, cascading destruction, and hierarchy blockers. The only gap is what the call returns on success or failure, which an agent may want when chaining deletes.

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 50%: site is documented ("as list_sites names it") and the description reinforces it as the account's site. post_id carries no description anywhere, though its name and integer type make intent obvious. Baseline 3 for partial coverage.

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 ("Deletes a post for good") and scopes it to a single site. It implicitly separates posts from pages via the page-hierarchy sentence, but never explicitly distinguishes itself from siblings like delete_site_page or unpublish_post, so an agent must infer that this is the post-specific destructive path.

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?

Permission rules are given ("Editors delete anything; an author their own drafts"), which tells the agent who may call it. However, there is no guidance on when to delete versus unpublish_post, finish_editing_post, or delete_site_page, so the choice among siblings is left to inference.

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