Challenge a decision against the brain (argue back with receipts)

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

With no annotations, the description carries the full burden, and it delivers: it discloses deterministic-only evidence, the meaning of silence, the fact that results are candidates rather than verdicts, that cards from another agent are flagged for coordination, and the dismissal workflow. This is unusually transparent about limits and side behaviors.

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 description is dense and information-rich, and the key when-to-use guidance is front-loaded. Some phrasing is heavy with parentheticals and jargon, but every clause contributes meaningful behavioral or usage context, so the length is justified.

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?

Despite having no output schema, the description explains what the output means ('Candidates, not verdicts', silence semantics), what evidence counts, what defaults apply, and how to act on results. For a moderately complex decision-support tool, this is complete enough for an agent to invoke it correctly and interpret its results.

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 100%, so the schema already documents claim, k, and canvas clearly. The description reinforces their roles—'one concise statement', candidate count, project-brain default—but adds little semantic depth beyond the schema. It earns the baseline 3 rather than more.

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 a specific verb and resource: it asks the brain to ARGUE BACK against a claim by surfacing deterministic contradictions, standing rules, reversed approaches, and colliding open questions. This clearly distinguishes it from generic brain querying and read tools, and the phrase 'Candidates, not verdicts' further defines its narrow role.

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 explicitly states when to use it: BEFORE committing to a significant decision. It also sets exclusions by warning against mere topical similarity and explaining that silence means 'no deterministic contradiction signal', not verified consistency. It even names the follow-up action and alternative tool relationship: brain_connect with relationship 'not_contradiction' for dismissing confirmed-false pairs.

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