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

Adds substantial context beyond the destructiveHint annotation: skipped candidates are counted, each queued candidate consumes the daily CV processing limit, the call is all-or-nothing when the limit would be exceeded, execution is asynchronous, and existing scores persist until new ones arrive. Auth requirements (OAuth/scoped token plus editable workspace role) are also stated.

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?

Front-loads the action and outcome, then layers eligibility, limits, async behavior, and auth in a logical order. It is on the long side with several compound clauses, but nearly every sentence carries operational information.

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 needed to explain the return value and does ('reports how many were queued and skipped'). For a two-parameter, non-idempotent batch mutation, an agent has everything required to call it and interpret the result correctly.

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 50%: workspaceId is documented in the schema, while batchId has no schema description. The description implies batchId identifies the screening ('candidates in a screening') but never explicitly maps the term to the parameter, so it only partially compensates for the gap.

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 and resource ('Queue criteria matching again for the candidates in a screening') plus the intent (scores recalculated against the role as it is now). This clearly distinguishes it from sibling mutations like update_role_criteria or restore_role_criteria, which change criteria rather than re-score candidates.

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 eligibility conditions — only completed, scored, non-archived candidates are processed, and a closed screening is refused. It does not name alternative tools (e.g. update_role_criteria) or explain when a caller should re-score versus adjust criteria, so it stops short of explicit routing.

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