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

Annotations already signal read-only/idempotent/safe, so the bar is lower — yet the description still adds deep behavioral context: spreads are gross and ignore Kalshi's fee schedule, pairings are matched by keyword overlap rather than a shared resolution source (pairing_unverified), unknown legs are never paired, and temporal_alignment null means 'could not be computed,' not 'aligned.' No contradiction with the annotations; readOnlyHint is consistent with a comparison tool.

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 (~400 words), but with no output schema it is the sole carrier of substantial output complexity (codes, flags, skipped counters, null semantics, fee caveat). It is front-loaded: purpose first, then mode selection, then response shape, then detailed safety semantics. Labeled sections (TWO MODES, RESPONSE, SAFETY FIELDS) make it scannable; minor redundancy ('in EITHER mode' repeated) keeps it from 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?

For a high-complexity tool with three optional parameters and no output schema, the description is remarkably complete: it documents both operation modes, the full response shape, every compatibility code, per-entry flags, skipped-leg counters, fee treatment, null semantics, and the reliability caveat. The only omissions (error behavior for unknown topics, a worked example response) are minor given how much is already covered.

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% with examples and the full topic list, so baseline is 3. The description adds genuine semantic value beyond the schema by explaining the mode relationship: topic is a pre-mapped shortcut, the explicit params override the topic-mapped side for custom pairings, and both modes invoke the identical token-overlap matcher. It clarifies mutual exclusivity and override behavior that the raw schema fields don't convey.

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 states a specific resource — 'Cross-venue spread between Kalshi and Polymarket for the same resolving question' — and the cross-venue framing immediately distinguishes it from the single-venue polymarket_* siblings. It also explains the signal's meaning (participant pool differences produce 2-25pp deltas), so an agent knows both what it does and why the output matters.

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 TWO MODES section gives explicit selection guidance: use `topic` for pre-mapped shortcuts and explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings, with both running identical logic. The closing warning ('pre-mapped ≠ tradeable', most topics return compatibility_warning today) is a clear when-not signal. It stops short of explicitly naming alternative sibling tools (e.g., polymorphic edges/arbitrage for single-venue cases), so it earns a 4 rather than 5.

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