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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses substantial behavior: it does not model Kalshi's fee schedule, reported spreads are gross rather than net tradeable edges, unmatched legs land in skipped_unclassified, warnings can be non-empty even when pairs are returned, and temporal_alignment=null means unknown rather than aligned. This is far more transparency than the annotations alone 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 well-structured with clear label segments: TWO MODES, RESPONSE, SAFETY FIELDS, and codes. It front-loads the core purpose and mode choice before diving into safety details. There is some redundancy around 'EITHER mode' and repeated warnings, which prevents a perfect score, but no sentence is filler given the absence of an output schema.

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 three optional parameters, the description carries the full burden of explaining response semantics, safety flags, compatibility codes, skipped counters, fee-treatment caveats, and temporal alignment behavior. An agent has enough information to call the tool correctly, interpret its results conservatively, and avoid treating raw spreads as tradeable edges.

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. The description adds meaningful semantic value by explaining the mode relationship: `topic` auto-fetches matching events, explicit tickers override the mapped side, and both modes feed the same token-overlap matcher. It also enumerates all recognized topic shortcuts, supplementing what the schema already lists.

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 names a specific operation and resource: computing the cross-venue spread between Kalshi and Polymarket for the same resolving question. It also flags the scope and the key caveat that the delta is only a real signal when bet shapes are equivalent, which distinguishes this from generic arbitrage or edge tools in the sibling list.

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 defines two mutually exclusive calling modes — `topic` for pre-mapped macros and explicit ticker/slug for custom pairings — and says both run the same matcher. It also warns that most pre-mapped topics currently return a compatibility warning and that pre-mapped does not mean tradeable, which is actionable guidance. It does not explicitly contrast with sibling tools like polymarket_arbitrage, so it stops short of a 5.

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