epistemic_consensus

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

With no annotations present, the description carries the full disclosure burden. 'Automatic hallucination veto' hints at a rejection capability, but it does not say what triggers the veto, whether the call is pure evaluation or records state, whether results are deterministic, or how a vetoed proposal surfaces. The BFT claim implies multi-agent corroboration but the single-call semantics are left unexplained.

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?

Two compact sentences, front-loaded with the tool's identity and followed by what it evaluates. Efficient, though the density of unexplained acronyms makes the brevity partly a liability rather than pure economy.

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 decision-gate tool with no output schema and no annotations, the description should explain the shape of the verdict and what each lattice tier implies, since those entries drive interpretation of the result. Neither is provided, leaving an agent unable to reason about the return value or act on a rejection.

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 description coverage is 100%, so the four parameters (agent_id, proposal, confidence, contradiction) are already documented with ranges. The description adds no meaning on top of that, which is the expected baseline when the schema does the work.

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 verb+resource are identifiable ('Evaluates agent proposals' via a consensus gate), but the core terms QATI, ZANNI_GHALIB, SHAKK and WAHM are opaque jargon with no gloss, so an agent cannot tell what the tiers mean or how the verdict is formed. It also fails to distinguish itself from the closely related siblings validate_claim and verify_step.

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?

There is no statement of when this gate should be used instead of validate_claim, verify_step or compute. No prerequisites, no exclusions, and no indication of what a caller should do with the result.

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