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

Annotations already declare readOnly=false, destructive=false and idempotent=true, so the safety bar is lower. The description still adds real context beyond them: decisions are visible to everyone in the role's workspace (a social/visibility consequence) and 'none' functions as an undo rather than a new state.

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 short sentences, front-loaded with the verb and resource, then the state values, then the optional note, then consequences. Nothing is padded or repeated from the name or title.

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?

With no output schema, the description carries the burden of stating side effects, and it does so for visibility and shortlist propagation. It leaves one notable gap: the reasons parameter's effect on the role's next_round is only explained in the schema, not in the description.

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 67% and the schema itself documents reasons and feedback_note thoroughly, including the enum values. The description only adds meaning for the decision enum (via 'none (undo)' and 'Optionally add a note'), and is silent on reasons and feedback_note, which carry non-obvious side effects (reasons feed next_round).

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 ('record a decision') and resource (a person in a role), and enumerates the three decision values. It names the downstream consumer get_shortlist, which aids discrimination, but does not distinguish itself from near-neighbours like score_candidate or next_round.

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?

'none (undo)' implies the reversal case, and 'Shortlisted people show up in get_shortlist' hints at where to verify results. However there is no explicit guidance on when to call this versus score_candidate or next_round, and no stated prerequisite that the username must already be in the role.

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