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

Annotations declare destructive=true and idempotent=true, and the description reinforces this with the critical operational fact that the dashboard offers no way back to New. It also discloses a side effect beyond the annotations: nothing is sent to the candidate.

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, zero waste; the precondition leads, then the irreversibility warning, then the side-effect note. Everything is front-loaded.

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?

Output schema exists so return values need not be described, and the description covers preconditions, failure mode, irreversibility, and side effects. Nothing an agent needs 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 0% for two required params, but job_id and application_id are self-describing identifiers and the description does not need to add syntax details. Baseline 4 applies since names are unambiguous.

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 (move) and resource (candidate), the exact target state (Reviewed), and the precondition (stage must be `new`). An agent can distinguish this from siblings like set_shortlist or reject_candidate without opening 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?

Explicitly conditions use on stage being `new`, names the failure (`candidate_not_new`) for other cases, and adds a procedural warning to ask the member first because the dashboard cannot reverse it. This is a complete when-to-use and when-not-to-use instruction.

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