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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral detail well beyond them: compatibility_codes can be non-empty even with matched pairs, temporal_alignment null means unknown rather than aligned, spreads are gross rather than net because Kalshi fees are not modeled, and unclassified legs are never paired. The description also clarifies that output flags can be non-empty and must be read, which is the kind of extra context an agent needs.

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 organized into labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS, Codes), which makes the density navigable. The core purpose and modes are front-loaded, and nearly every sentence carries operational or safety-relevant information. Some redundancy and sheer length prevent a 5, but the structure is effective for such a complex tool.

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 correctly carries the burden of explaining return values: leg-by-leg raw probabilities, spread[].top_spreads_pp, compatibility fields, temporal_alignment, fees_note, and skipped counters. It also covers failure and skip semantics, such as unclassified legs never being paired and null alignment meaning unknown. An agent has enough context to invoke the tool and interpret its results 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 is 3. The description adds useful mode-level semantics: topic auto-fetches the matching event on each venue, and both modes run the identical token-overlap matcher. It reinforces the override relationship between explicit parameters and topic-mapped sides, though it does not introduce significant new format details 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 description opens with a specific verb and resource: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It clearly describes the two modes and the nature of the output. It does not explicitly contrast the tool with sibling tools like polymarket_arbitrage, so it stops just short of full sibling differentiation.

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 explicitly separates the topic mode (pre-mapped shortcuts) from the explicit pairing mode (custom kalshi_event_ticker + polymarket_event_slug), telling the agent which parameters to use for which scenario. It also gives clear cautionary guidance: most pre-mapped topics return compatibility warnings, and pre-mapped does not mean tradeable. It does not name alternative sibling tools or provide explicit when-not-to-use routing to them.

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