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

Annotations already flag destructive=true, idempotent=true, openWorld=false, but the description adds meaningful context beyond them: it names the durable execution registry, promises no duplicate effects, lists the consent/permission requirements, and discloses the optimistic-concurrency rule (read current state and use its current revision). That is genuinely useful behavioral detail for a destructive mutation.

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?

Three sentences, front-loaded with the core action and then the preconditions and revision rule. Dense but every sentence carries information; 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?

An output schema exists so return values need no explanation, and the description covers auth tiers, consent, idempotency, confirmation, and revision handling for a complex destructive retry tool. The main shortfall is the undocumented project_id/target_id semantics, but overall it is close to complete.

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 0%, so the description must carry parameter meaning. It partially does: 'idempotency key' maps to idempotency_key, 'exact-intent confirmation' maps to the confirmed/confirmation_token fields, and 'use its current revision' maps to expected_version. But project_id and target_id are never explained, leaving notable gaps at zero schema 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 (retry) and resource (the exact existing failed internal action) plus a scoping constraint (no duplicate effects via the durable execution registry). This clearly separates it from execute_action or approve_action by emphasizing 'exact existing failed' action, though it never names a sibling 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?

Gives concrete preconditions for use: Startup tier or higher, read+write consent, stable idempotency key, exact-intent confirmation. However, it never states when to choose this over the sibling execute_action/approve_action, nor any when-not conditions, so the selection logic is only implied by the word 'failed'.

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