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

Annotations (readOnlyHint=true, idempotentHint=true) already mark this safe, and the description adds substantial non-obvious behavior: pairing is by keyword/word overlap rather than a shared resolution source (pairing_unverified), spreads are gross of Kalshi fees, temporal alignment null does NOT mean aligned, and unclassified legs are never paired. These disclosures meaningfully exceed annotation coverage with zero contradiction.

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 quite long (well over 400 words) and densely packed. It is well-organized with clear section markers (TWO MODES, RESPONSE, SAFETY FIELDS) and every sentence earns its place given there is no output schema to carry return-format detail. However, it is not front-loaded — the safety codes and temporal-alignment discussion push the core example toward the tail — and some prose could be tightened.

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 3-param, two-mode tool with no output schema, the description does the heavy lifting admirably. It covers mode selection, response shape (raw probabilities, top_spreads_pp, skipped_unclassified, low_confidence_pairs), all compatibility codes, temporal-alignment semantics, the fees_note caveat, and skipped-comparison counters. Nothing an agent needs to interpret results correctly is missing.

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% (all three params are documented in the schema), so baseline is 3. The description adds real value beyond the schema by explaining the mode semantics — that 'topic' auto-fetches matching events on each venue via 10 named shortcuts, and that either explicit override runs the identical token-overlap matcher. This mode interplay is not captured in the schema's per-parameter lines.

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 line is precise: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' It names both venues and the comparison operation, distinguishing itself from single-venue siblings like polymarket_edges and polymarket_arbitrage. The subject of comparison — same-outcome pricing delta — is unambiguous.

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 spells out two modes with explicit selection criteria ('topic' for pre-mapped macro shortcuts, explicit ticker+slug for custom pairings) and notes both run the identical matcher. It also warns that 'pre-mapped ≠ tradeable' and that real spreads are rare, shaping expectations. However, it never names an alternative sibling tool to use instead, leaving when-not-to-use implicit rather than explicit.

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