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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description usefully explains what that means in practice: dry_run true only reports what would run and quota used, while dry_run false actually launches the job. It also discloses a gating condition (paid feature, stages must be approved) that annotations cannot express. It does not state whether recorded decisions are reversible or what happens to prior decisions.

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 trigger condition is front-loaded and every clause carries information: action mapping, the reason requirement, the dry_run default, and the paid-feature gate. The middle section is a dense run-on chain that could be split per action for faster scanning.

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 7-parameter multiplexed tool with no output schema, the description covers the mode selection, the safety default, the cost prerequisite, and the one conditional requirement (reason on exclude). What is missing is modest: whether decide is a separate step from run, and any indication of what a dry-run versus launch response contains.

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 86%, so the baseline is 3, but the description supplies the missing semantics for the action enum, which the schema lists only as bare values, and reinforces that exclude needs a reason and that dry_run defaults to true. Minor parameters such as idempotency_key and paper_id are left entirely to the schema.

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 three concrete operations (fetch open-access full texts, run AI full-text screening, decide/record a decision) and attributes each to an action value, so an agent can map intent to parameter immediately. It does not explicitly distinguish itself from the sibling revisia_fulltext (the non-act variant), leaving the read-vs-write split to be inferred from naming convention.

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?

The opening 'Use this when the researcher wants...' clause gives per-action trigger conditions, and it adds real prerequisites: exclude requires a reason, fetch/run default to dry_run true, and screening is a paid feature needing approved stages. It stops short of naming which sibling to use instead for status/listing or approval (revisia_fulltext, revisia_approve_stage).

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