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

Annotations already mark this as read-only, idempotent, and non-destructive, so the description adds substantial behavioral context beyond those hints. It discloses that compatibility_warning and compatibility_codes can be non-empty even when matches exist, that pairing is always unverified, that temporal_alignment null means 'could not compute' rather than aligned, that Kalshi fees are not modeled, and that spreads are gross not net — far more than annotations supply.

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 tool is complex and lacks an output schema, so nearly every clause carries necessary information about modes, safety fields, flags, skipped legs, and fee disclosures. It is front-loaded with the core purpose and organizes distinct concerns with clear markers like 'TWO MODES', 'RESPONSE', and 'SAFETY FIELDS'; still, it reads as a dense wall of text and could benefit from formatting into sections.

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?

Because there is no output schema, the description carries the full burden of explaining the return shape, and it does so thoroughly: leg-by-leg prices, top_spreads_pp, per-entry flags, skipped_unclassified, low_confidence_pairs, temporal_alignment, fees_note, and skipped counters. It also covers crucial edge cases like null temporal alignment, non-empty warnings despite positive matches, and the unverified nature of every pairing — leaving little ambiguity for an agent.

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%, giving the baseline of 3, but the description adds meaningful behavioral semantics beyond the schema. It explains that one mode uses pre-mapped shortcuts while the other takes explicit tickers/slugs, that both modes run the identical overlap matcher, and that explicit values override topic-mapped sides — context that helps an agent choose parameter combinations correctly.

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 ('Cross-venue spread between Kalshi and Polymarket for the same resolving question') and clearly identifies the resource. It differentiates itself from likely sibling tools by naming its two operating modes and what it returns, so an agent can tell it apart from related market-analysis tools.

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 usage context: when bet shapes are equivalent the spread is a signal, when they are not the tool flags it, and both pre-mapped and explicit modes run the same matcher. It does not explicitly name an alternative tool to use instead, but the caveat that most pre-mapped topics return compatibility_warning and that pre-mapped is not tradeable gives practical guidance about when to distrust results.

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