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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes beyond them by disclosing that no publication side effect ever occurs, that a revision spawns a new attempt only if the concurrent transaction wins, and that the call requires the 'act' scope and costs nothing. The 'inspected' precondition on legacy results is additional behavioral context not present in annotations.

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?

Roughly 45 words across four short sentences, with the purpose and operations front-loaded. Every sentence adds a distinct fact — operation set, transactional revision behavior, no-publish guarantee, cost/scope — and there is no filler.

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 an 11-parameter, four-mode, CAS-guarded tool with no output schema, the description is too thin: it omits how the expected_* fields serve as concurrency tokens, what the response contains (e.g., a new attempt id after revise), and which parameter combinations are valid per operation. The schema's operation description fills the adopt_legacy_result gaps only; the rest is left to the agent.

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 description coverage is only 18% (just operation and expected_attempt_id are documented), and the description only loosely compensates with the 'transaction wins' phrase. It never explains the optimistic-concurrency parameters (expected_move_updated_at, expected_legacy_updated_at, expected states) or which parameters apply to each operation, so an agent must infer the CAS mechanics from the operation enum text alone.

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 action ('Apply one explicit founder review decision') on concrete resources ('current managed attempt', 'unfinished work', 'legacy result', 'recorded publication') and enumerates the four operation modes (revise, withdraw, adopt_legacy_result, correct_publication). These operations are unique among the move-family siblings (accept/archive/propose/ship/skip/undo), so an agent can distinguish it without inspecting 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?

Provides clear context: 'This never publishes anything' rules out the tool when a publication effect is desired, revision is gated on the transaction winning, and it requires the 'act' scope and is free. It stops short of explicitly naming sibling alternatives, so the when-not-to-use guidance is implied rather than fully stated.

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