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

Even though annotations already declare readOnlyHint/openWorldHint/idempotentHint, the description adds an exceptionally rich behavior picture: safety fields can be non-empty even with matched_pairs>0, compatibility_codes semantics, temporal alignment specifics, a standing fee disclosure stating spreads are gross, and exact handling of unclassified legs. This far exceeds what annotations provide and helps the agent interpret results correctly.

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 earns its length by covering many non-obvious edge cases that cannot be inferred from schema or annotations. It is front-loaded with the core purpose and uses clear mode/response/safety markers. It could be tighter (some repeated references to the same matcher and warnings), which keeps it at a 4 rather than a 5.

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 bears the full burden of explaining return semantics — and it does: top_spreads_pp values are Kalshi minus Polymarket, spread.skipped_unclassified and low_confidence_pairs exist, temporal_alignment can be null, and fees are gross rather than net. For a complex comparison tool this is a complete invitation to call it 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% and explains the topic values, ticker, and slug, so the baseline is 3. The description adds the mode relationship — topic alone OR the explicit pair, with both modes running the same matcher and 'overrides' behavior — which meaningfully helps an agent choose/combine parameters 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 purpose is unmistakable — it computes a cross-venue probability spread between Kalshi and Polymarket for the same resolving question — and it distinguishes two modes. It does not use an explicit action verb like 'compute' or 'get' in the opening sentence, and it does not contrast itself with sibling tools such as polymarket_arbitrage, but the resource and relationship are specific enough for an agent to know when to call it.

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 concrete usage guidance: use topic for 10 pre-mapped shortcuts, or provide kalshi_event_ticker + polymarket_event_slug for custom pairs, and warns that most pre-mapped topics currently return compatibility_warning and are not necessarily tradeable. It does not name alternative tools or explicitly say when not to use this versus polymarket_arbitrage, so it stops 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.