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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=falsechers. The description adds important behavioral nuance beyond those hints: it explains the three-way equivalence outcome, the confidence threshold for comparing, and the specific-versus-generic source rule that prevents false conflicts. It also discloses that the tool internally runs resolution_audit, which is useful to set expectations.

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 information-dense and front-loaded with the core purpose, but it is long and contains a lengthy parenthetical example and an extended heuristic explanation. Every point is relevant, but the phrasing is verbose and could be tightened or restructured with bullet-like separators. It earns its content but sacrifices conciseness.

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?

There is no output schema, so the description carries the burden of explaining return values, and it does so thoroughly: it explains the possible values of `equivalent` (true/false/unclear), mentions `differing_fields`, and instructs the caller to read `raw_clause` in unclear cases. It also covers the non-conflict heuristic. The only gap is not fully specifying the entire output structure or exact field locations, but the guidance is sufficient for the agent to decide when to call it.

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% with both parameters described as 'First market to compare' and 'Second market to compare.' The description adds that they are markets on either Polymarket or Kalshi and that the tool runs resolution_audit on both sides, which slightly clarifies roles. However, it does not add meaningful detail beyond the schema's enum and nested-object definitions, so a baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Field-by-field diff of TWO markets' settlement clauses.' It clearly states that the tool runs resolution_audit on both sides and compares source, settle time, precision, and evidence standard, which differentiates it from the sibling resolution_audit. The three-way return value is also summarized, leaving no ambiguity about the tool's core function.

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 description gives explicit usage context: 'Use this before sizing a polymarket_kalshi_spread pair as a real cross-venue arb, or standalone to sanity-check any two markets you suspect settle on different things.' This clearly states when to use the tool. It does not, however, explicitly name alternatives or say when not to use it, so it stops short of a full when/when-not guide.

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