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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior, and the description adds substantial behavioral detail beyond those: compatibility_warning can be non-empty even when matched_pairs>0, unknown metric_type/match_subtype legs are never paired, temporal_alignment null means 'could not be computed' rather than 'aligned', Kalshi fees are not modeled so spreads are gross, and matching is based on keyword overlap rather than a shared resolution source. There is no contradiction with annotations.

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 long, but the purpose is front-loaded and major sections are labeled with uppercase cues like TWO MODES, RESPONSE, and SAFETY FIELDS. Almost every sentence carries a distinct safety, matching, or fee-disclosure fact needed because there is no output schema, though the prose is dense and could be tightened with bullet formatting and minor removal of redundancy.

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, yet the description compensates by explaining the response shape in detail: leg-by-leg raw probabilities, top_spreads_pp, compatibility_codes, per-entry flags, temporal_alignment, fees_note, and skipped counters. It also covers edge cases and failure modes well enough for an agent to call both modes correctly.

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% for all three parameters, so the baseline is 3, but the description adds meaningful semantics: `topic` is expanded into ten named shortcuts, explicit ticker and slug parameters are described as overriding the topic-mapped side, and both modes are stated to run the identical token-overlap matcher. That goes beyond simple schema documentation.

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: it computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It also gives two concrete operation modes, topic shortcuts versus explicit ticker/slug pairings, which clearly distinguishes it from Polymarket-only siblings like polymarket_edges or polymarket_arbitrage.

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 clear when-to-use context: use the `topic` shortcuts for pre-mapped macros, or use explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings, and it warns that most pre-mapped topics currently return compatibility warnings and that pre-mapped is not the same as tradeable. It does not explicitly name alternative sibling tools or state when not to use this tool, so it falls just short of a 5.

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