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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true; the description adds genuinely new context by flagging that drafting is a paid feature and gated on the extraction stage, plus that dry_run defaults to true. However, it does not disclose what destructive means here — e.g. whether decide overwrites existing judgements or domain entries — leaving the most consequential annotation unexplained on a mutation tool.

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-loaded with a 'Use this when' clause and kept to two sentences covering run and decide, plus cost/gating. It is dense with parentheticals but every clause carries operational meaning; a light split into separate run/decide sentences would improve scanability slightly.

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 two-mode mutation tool with 7 parameters and no output schema, it covers prerequisites, cost, and the dry-run default well. What is missing is outcome information an agent needs to act safely: whether run returns a job handle, and whether decide is additive or overwriting — important given destructiveHint=true.

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 schema already labels tool, domains, dry_run, paper_id, project_id, and idempotency_key. The description restates the two key semantics (dry_run false launches; decide takes instrument plus one judgement per domain) without adding format or constraint detail beyond what the property descriptions already say. Baseline 3 applies given the schema does the heavy lifting.

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 both modes precisely: 'AI risk-of-bias drafts (action run...)' and 'a judgement recorded (action decide...)', each mapped to its action value. An agent can distinguish the two operations without opening the schema. It stops short of 5 because it never contrasts with the read-only sibling revisia_rob, which an agent choosing between list/inspect and act tools would want.

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 an explicit trigger condition ('Use this when the researcher wants...') for each action and states a prerequisite ('needs the extraction stage approved'). No exclusion clause or alternative tool is named, so an agent must infer that revisia_rob covers inspection rather than drafting or recording.

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