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

Beyond the annotations it discloses the confirmation handshake, that the first call is a no-op validation pass, that unknown fields are refused by name, and that the first call returns a summary and confirm_token. This is exactly the behavior an agent needs and cannot infer from readOnlyHint=false or destructiveHint=false.

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 purpose and auth, then the flow in short clauses; no filler. A few terse constructions ('Two calls. The first changes nothing') trade grammar for density but stay readable.

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 no output schema, it covers permission, the two-phase protocol, validation failure mode, and the first call's return payload. It stops short of saying what the second call returns or whether a restore can fail after confirmation.

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% and confirm_token is already described there, but the description adds the sequencing rule (omit first, supply on the confirmed second call with identical arguments), which is real meaning beyond the field text.

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 ('Undo deleting a post') that is unambiguously the inverse of the sibling delete_post, so an agent can pick it without opening the schema.

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 a clear when/how: requires content:write, and the two-call sequence with a human confirmation gate before the second call. It does not explicitly name delete_post as the operation being undone or state when to prefer a different tool, but the procedural guidance is unusually concrete.

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