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

Annotations already carry readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description richly exceeds that baseline by disclosing: fees are not modeled (spreads are gross, not net tradeable edge), temporal_alignment null does NOT mean aligned, compatibility_codes can be non-empty even with matched_pairs>0, and unknown metric_type/match_subtype legs are never paired. No annotation 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 long, but every block earns its place given the tool's genuine complexity. It is well-structured with visible labels (TWO MODES, RESPONSE, SAFETY FIELDS) and the core purpose is front-loaded before the machinery. It loses one point for density — the volume of codes and caveats in a single prose wall requires careful reading — but nothing is redundant.

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 tool with no output schema, the description fully compensates: it details the response shape (leg-by-leg prices, top_spreads_pp, safety fields), enumerates every compatibility code, explains the skipped/lop_confidence_pairs mechanics, and closes with the gross-vs-net fee caveat. Given three modes, nested safety fields, and temporal-alignment semantics, nothing an agent needs to call it 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%, so baseline is 3, but the description adds substantial semantics beyond it: it enumerates all 10 topic macro values and their meaning, explains that explicit kalshi_event_ticker/polymarket_event_slug OVERRIDE the topic-mapped side, and states that both parameter paths execute the identical token-overlap matcher with identical disclosures. This interaction logic is not present in the schema itself.

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 precise statement of scope: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' A single sentence captures verb (compute/compare spread), resource (Kalshi vs Polymarket events), and the distinguishing constraint (same resolving question, cross-venue). This cleanly separates it from single-venue siblings like polymarket_arbitrage and polymarket_edges.

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 documents TWO MODES with explicit selection criteria: topic shortcuts for pre-mapped macros, and explicit ticker/slug for custom pairings, noting both run the identical matcher. It also gives practical guidance that most pre-mapped topics return compatibility warnings and that pre-mapped ≠ tradeable. It does not explicitly name sibling alternatives or state when NOT to use this in favor of another tool, which keeps it just below a 5.

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