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

Even though annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint: false, the description goes far beyond them. It discloses matching limitations (keyword/word-overlap not shared resolution source), fee treatment ('spread_pp is gross, not a net tradeable edge'), safety fields that can be non-empty even when pairs are returned, skipped-leg counters, and the meaning of temporal_alignment null. There is no contradiction with 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 tightly structured: purpose, TWO MODES, RESPONSE, SAFETY FIELDS, and closing caveat. It is front-loaded with the core purpose and uses labeled sections. Some content, like the repeated topic list, overlaps with the schema, but the length is largely earned given the number of non-obvious safety codes and edge cases an agent must know to use the tool correctly.

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?

With no output schema, the description carries the full burden of explaining return behavior, and it delivers: leg-by-leg prices, top_spreads_pp with per-entry flags, compatibility_codes, spread.skipped_unclassified, low_confidence_pairs, temporal_alignment semantics, fees_note, and skipped counters. It also clarifies the meaning of null temporal_alignment and explains why compatibility_warning can coexist with matched pairs. An agent has enough to know what to expect and how to interpret results.

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, but the description adds substantial meaning beyond the schema. It explains how the three parameters interact in two modes, that 'BOTH modes run the identical token-overlap matcher', that explicit parameters override the topic-mapped side, and that the same safety disclosures apply in both modes. This gives an agent the full parameter-interplay model rather than just per-field 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 specific verb and resource: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' It also immediately clarifies the object being measured (the spread between two venues) and the condition under which it is meaningful ('when the bet shapes are equivalent'), setting it apart from the sibling tools such as polymarket_arbitrage or polymarket_edges without any ambiguity.

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 clearly explains the two calling modes — topic shortcuts versus explicit kalshi_event_ticker + polymarket_event_slug — and when each is appropriate. It also gives an important usage warning: 'Real cross-venue spreads are rarer than the macro-shortcut list suggests... pre-mapped ≠ tradeable.' It does not explicitly name sibling alternatives or state 'use this instead of X', so it stops short of a full 5.

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