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

Annotations already declare destructive=true and idempotent=true, so the safety profile is covered structurally. The description adds genuine context beyond them: the retry replays identical saved request/revision/grants (including access removals) and a conflict forces a fresh reviewed selection rather than a forced replay. It does not detail what a conflict response looks like or the blast radius of the access removal.

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?

Two sentences, front-loaded with the action ('Explicitly retry...') followed by replay semantics and the conflict caveat. Dense but every clause carries meaning; wording like 'complete replacement grants' is slightly compressed but not wasteful.

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 destructive, idempotent retry mutation with no output schema, the description covers the key decision points: identical replay payload and conflict handling. Minor gaps remain around what 'receipt' inspection entails and the timing/failure semantics, but nothing essential to invoking it correctly is missing.

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%: projectId and idempotencyKey are documented in-schema, while selectionId and selectionRevision are not. The description references 'revision' and 'complete replacement grants' but adds no format or expected-value meaning beyond the schema, so it only marginally compensates for the undocumented half.

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 ('retry') and resource ('library access command') and frames it as the replay of an original command rather than a fresh application. It implicitly distinguishes itself from sibling 'apply'/'inspect'/'dossier_library_access' tools via 'retry the original ... after inspecting its receipt', but never names those siblings explicitly.

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?

Specifies the triggering condition ('after inspecting its receipt') and the exclusion path ('a conflict requires a fresh reviewed selection'), which tells the agent when this tool is the wrong one. It stops short of naming the alternative tools explicitly, so routing still requires inference from the sibling list.

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