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

Annotations only provide read-only, open-world, idempotent, and non-destructive hints; the description goes far beyond them. It discloses the token-overlap matching method, defines every compatibility code, explains that unclassified legs are never paired, and clarifies that null temporal_alignment means unknown rather than aligned. It also discloses that spreads are gross of Kalshi fees, making the behavioral surface unusually transparent.

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 dense but front-loaded: purpose first, then modes, then response shape and caveats. Some redundancy exists, such as repeated 'same disclosures apply' and 'in EITHER mode' qualifiers, and the compatibility-code list could be better structured as bullets. Still, nearly every sentence carries a distinct operational fact needed to call the tool correctly.

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 fully compensates by explaining return values: 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 failure cases, such as compatibility_warning being non-empty even when matched_pairs>0, and the fee-modeling limitation. An agent has enough information to call and interpret the tool 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%, so the baseline burden on the description is low and the schema already documents parameter meanings and override behavior. The description adds semantic value by explaining that both modes run the identical token-overlap matcher and that `topic` values auto-fetch the matching event on each venue. This meaningfully enriches parameter understanding beyond the schema.

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 opening sentence names the exact function: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It distinguishes this from single-venue or arbitrage tools by emphasizing the two-venue comparison and by clearly framing the two modes. The extensive caveats reinforce what the tool does without obscuring 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 explicit mode-selection guidance: use `topic` shortcuts for ten pre-mapped events, or provide explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings. It also warns that most pre-mapped topics currently return compatibility warnings, which tells the agent when results are untrustworthy. However, it never names or contrasts sibling tools like polymarket_arbitrage or polymarket_edges, so 'when to use this instead of X' is only implicit.

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