review_decision

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

With no annotations, the description carries the full burden and does so thoroughly: it enumerates what prepare returns, states that acceptance replaces the operative revision and retirement withdraws the entire record including its proposal, notes that changed records or code invalidate the token, and warns that identities/approvals are recorded assertions rather than authenticated proof. This is exactly the behavioral context an agent needs before mutating a record.

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?

The prepare-phase return contents and the verdict workflow are front-loaded, and each sentence carries distinct information (returns, consequences, prerequisites, token invalidation, trust caveat). It is dense and somewhat long, but nearly every clause earns its place; only minor tightening is possible.

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 six-parameter tool with no output schema and no annotations, the description covers the full lifecycle: what prepare yields, how verdicts are recorded, the prerequisites for acceptance, the destructive effect of retirement, token staleness rules, and the trust model. Nothing essential for correct invocation 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 100%, so the baseline is 3, but the description adds real meaning: the reviewToken is tied to the prepared review and rejects stale record/code revisions, the note is the rationale required for a verdict, the reviewer must be the actual identity and never invented, and action distinguishes the read-only prepare from authorized verdicts. This goes beyond the schema's field descriptions.

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?

The description states a specific verb+resource ('prepare a decision review' / 'record accept, reaffirm, or retire') and cleanly separates the read-only prepare mode from the mutating verdict modes. It is unambiguous about what the tool does. It does not, however, differentiate itself from siblings like review_advisory or save_decision, which an agent must still infer.

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?

It gives a clear workflow: prepare first (read-only) to obtain the token, then record a verdict using that token, reviewer, and reason, and it lists the conditions for acceptance (owner, source, readable Git HEAD, committed anchor changes). It stops short of naming when to choose this over review_advisory or how verdict actions relate to save_decision, so exclusions and alternatives are absent.

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