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

The annotations already declare readOnly, idempotent, and non-destructive behavior, and the description goes well beyond that: it discloses that compatibility fields can be non-empty even when pairs are returned, that unknown legs are never paired, that temporal_alignment null means 'could not be computed' not 'aligned,' that spreads are gross and exclude Kalshi fees, and that flagged mismatches may mean different questions. This is rich, honest behavioral disclosure with no contradiction of annotations.

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 well-structured with explicit section markers: TWO MODES, RESPONSE, SAFETY FIELDS, Codes, and fee disclosures. Nearly every sentence adds operational value, though some details are repeated or could be tightened, such as the overlapping discussion of compatibility flags in the SAFETY FIELDS section and again on top_spreads_pp entries.

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 carries the full burden of explaining the response, and it does so thoroughly: leg-by-leg prices, spread entries, safety fields, compatibility codes, flags, skipped-leg counters, temporal alignment semantics, fee caveats, and the practical warning that many macro shortcuts are not currently tradeable. An agent has enough information to invoke the tool and interpret the result in both modes.

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 covers all three parameters at 100%, but the description adds substantial meaning: it explains the topic mode's shortcut list, explicit ticker/slug overrides, and that both modes run the same matcher and produce the same disclosures. It also clarifies that kalshi_event_ticker and polymarket_event_slug override their topic-mapped counterparts, which is not apparent from the schema alone.

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, unambiguous statement: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' It names the exact resources (Kalshi and Polymarket), the output concept (spread), and the condition for meaningful comparison, making it clearly distinguishable from sibling tools like polymarket_edges or polymarket_arbitrage.

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 strong context for when to use the tool: it explains the two modes, notes that both run the identical token-overlap matcher, and warns that most pre-mapped topics currently return a compatibility_warning and that 'pre-mapped ≠ tradeable.' It does not explicitly name alternative sibling tools or provide an explicit 'use tool X instead' rule, 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.