Review Agent Promotion (Unavailable)

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

Annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is fully consistent with them while adding critical context not present in the structured fields: no review is created, nothing is signed, and promotion history is untouched. For a mutation-sounding verb like 'review', this side-effect disclosure is exactly what prevents a wrong call.

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 with the availability status front-loaded in the first four words. Every sentence carries distinct information: the SDK version, the consequence, and the three specific non-effects.

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?

Nothing an agent needs is missing. It knows the tool is dead, why, and that it is side-effect free, so no output schema or further behavioral detail is required. Adding parameter guidance would be noise for a tool that cannot run.

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 100% and each of the seven parameters (scope, toTier, agentId, verdict, reasoning, principalId, probationDays) is documented in the schema itself. The description adds no parameter-level detail, which is defensible since the call always fails, but it neither compensates for nor extends the schema, so the baseline 3 applies.

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 names the specific operation (promotion review creation) and immediately qualifies it as unavailable, so an agent knows both what the tool nominally does and that it cannot succeed. It is trivially distinguishable from siblings like get_promotion_history, which remains functional.

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 explicit when-not-to-use guidance: the tool returns an error on every call, so it should never be invoked. It stops short of naming the alternative an agent should use instead (e.g., get_promotion_history) for reading promotion state, which is the only remaining gap.

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