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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the safety and repeatability profile is carried structurally. The description adds useful context that current content is replaced by an earlier revision and that a human-readable result appears in `say`, but it never says whether the current version is preserved or recoverable. No contradiction with the annotations, though 'restore' semantics sit somewhat uneasily next to 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?

Short and front-loaded: the action comes first, then the two non-obvious parameters, then the output note. Every clause carries information, with only minor terseness in the 'revision: which earlier one' phrasing.

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 four-parameter mutation tool with no output schema and thin schema coverage, the description covers the value space of the non-obvious parameters and points at the `say` field for results. The remaining gap is behavioral — what happens to the overwritten content and whether a valid revision must pre-exist.

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 only 25% (only application_id is documented), so the description must compensate, and it does: it enumerates the legal values for `what` (all, cover_letter, cv, answer), notes that `question` accompanies the 'answer' case, and explains `revision` as 'which earlier one'. Only application_id is left to the schema, which handles it.

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: put part of an application (all, cover_letter, cv, or answer) back to an earlier revision. An agent can tell what the tool does, but nothing distinguishes it from sibling undo_change or edit_application, so it falls short of a 5.

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?

There is no explicit when-to-use guidance: no statement of prerequisites (does a revision history need to exist?), no condition comparing it to undo_change, and no when-not-to-use. The 'what'/'revision' enumeration describes parameter values rather than usage context.

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