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

Annotations already establish readOnly/idempotent/non-destructive behavior, and the description goes well beyond them by detailing compatibility warning codes, fee treatment (Kalshi fees not modeled, gross spreads), skipped comparison counters, and the rule that legs with 'unknown' metric_type/match_subtype are never paired. This gives an agent the behavioral context needed to interpret warnings and returned data 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 and dense, but the tool is complex and the length is mostly earned by critical caveats around safety fields, temporal alignment, and fee disclosures. It is front-loaded with the core purpose and modes, and uses clear structural labels like 'TWO MODES', 'RESPONSE', and 'SAFETY FIELDS'. There is some repetition around 'EITHER mode' and the final 'pre-mapped ≠ tradeable' reminder, so it is not maximally concise.

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?

Given that there is no output schema, the description is remarkably complete: it documents the response shape, how spreads are computed, when compatibility warnings appear, what each compatibility code means, temporal alignment semantics including null handling, fee limitations, and skipped comparison types. An agent has enough context to call the tool and interpret its results without guessing.

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 input schema covers all three parameters, so the baseline is 3, but the description adds substantial semantic value: it explains what `topic` shortcuts auto-fetch, that `kalshi_event_ticker` and `polymarket_event_slug` override the topic-mapped side, and that both modes execute the identical token-overlap matcher. This is meaningfully beyond the schema's descriptions.

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 clear resource and purpose: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' and further clarifies two modes and pre-mapped shortcuts. It distinguishes itself from siblings mostly through the 'cross-venue' framing, but it never explicitly names or contrasts sibling tools like polymarket_arbitrage, so a perfect score isn't warranted.

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 within-tool guidance: use `topic` for pre-mapped shortcuts, use explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings, and says both modes run identical matching logic. It also gives strong when-not guidance such as 'pre-mapped ≠ tradeable' and tells agents to verify close/strike dates manually when temporal alignment is unknown. It does not compare against sibling tools by name, so the 'alternatives' aspect is only partially covered.

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