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

Annotations already mark this read-only and non-destructive, and the description goes far beyond them by disclosing pairing caveats: compatibility fields can be non-empty even when pairs are returned, unknown legs are never paired, temporal_alignment null means 'could not be computed', and all spreads are gross because Kalshi fees are not modeled. It also defines every compatibility code and explains skipped counters, so the agent understands exactly what the tool will and will not guarantee.

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 it is logically ordered from purpose to modes to response fields to safety caveats, and it uses labeled all-caps segments to improve scannability. It is dense rather than redundant, though a single block of prose could be better formatted with bullets or section breaks for easier agent parsing.

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?

With no output schema, the description carries the full burden of explaining return semantics, and it does so thoroughly: leg prices, top_spreads_pp, compatibility codes, per-pair flags, temporal_alignment, fees_note, skipped counters, and the rarity caveat are all covered. Nothing essential for safe invocation or interpretation appears to be missing.

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?

The schema already documents all three parameters at 100% coverage, so the baseline is 3; the description adds meaningful mode logic by defining topic as a set of 10 shortcuts and the pair of explicit identifiers as an override path, and by noting that both modes run identical matching. It could specify combination rules more precisely, such as whether mixing topic with one explicit override is valid, but it compensates well overall.

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 by identifying exactly what the tool produces—a cross-venue spread between Kalshi and Polymarket for the same resolving question—and consistently ties every output field back to that cross-venue comparison. It clearly names both venues and the scope, so an agent can distinguish it from related sibling tools without inspecting their schemas.

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 operational context: two explicit call modes (topic shortcut vs explicit kalshi_event_ticker + polymarket_event_slug) and states that both modes run the same matching logic. It also cautions that pre-mapped topics often return compatibility warnings and are not automatically tradeable. It does not explicitly name alternatives or provide formal when-not-to-use rules, but the mode guidance and caveats give strong direction.

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