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

Annotations already mark this readOnly/idempotent/non-destructive, and the description adds substantial behavioral disclosure: the compatibility warning/codes, the token-overlap matching method, the fee caveat, the handling of 'unknown' legs, and the meaning of temporal_alignment null. This goes well beyond what annotations provide.

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 structured with clear labels (RESPONSE, SAFETY FIELDS, Codes, etc.) and front-loads the core purpose. Some repetition and exhaustive code listings could be trimmed, but for a tool with no output schema the density is largely justified.

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 and an open-world, safety-sensitive result set, the description compensates thoroughly: it explains return fields, flag codes, skipped counters, fee handling, and the meaning of null alignment. An agent has enough information to invoke it correctly and 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?

Although the schema already covers all three parameters, the description adds real semantic value: the distinction between pre-mapped topics and explicit overrides, the exact valid topic values, the override relationship, and the claim that both modes run the same matcher. This is meaningful guidance beyond the schema text.

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 identifies a specific resource — the cross-venue spread between Kalshi and Polymarket for the same resolving question — so an agent can tell what the tool computes. It lacks a strong verb and never differentiates itself from closely related siblings like polymarket_arbitrage, so it stops one step short of full differentiation.

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 (`topic` shortcuts vs explicit ticker/slug) are described with concrete examples, and the description gives clear warnings about when output is reliable (equivalent bet shapes) versus when it is not. It does not explicitly name alternative sibling tools or state when to prefer one of them, so there is context but no explicit exclusion.

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