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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds the meaningful behavioral fact that these rules are static and can be cached rather than polled ('to renew rules'). It stops short of batch failure semantics — what happens if one address in the array is invalid or unknown — which would matter for a 200-item call.

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?

Two sentences, front-loaded with purpose and followed by the routing/exclusion clause. Every clause carries information: scope, content, cap, alternative, and exclusions.

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 an output schema present, return-value detail is correctly omitted, and the description covers scope, cap, and exclusions for a simple two-parameter batch read. The only real gap is cross-chain/mixed-address behavior and partial-failure handling.

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 50%: both top-level params are documented, but the array itself carries only minItems/maxItems constraints. The description reinforces the 200-market cap, yet it never clarifies that all marketAddresses must belong to the same chainId, which is the main semantic risk in a batch call.

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 gives a specific verb and resource — 'Get static per-market orderbook trading rules' — and enumerates what those rules include (price grid, size floors, fees, TIF, STP) plus the batch scope ('up to 200 markets in one call'). That is enough to distinguish it from single-market readers like kellian_get_market without opening the schema.

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?

It names the alternative it replaces ('instead of polling kellian_get_market per market') and states the condition that selects it. It also lists what the tool explicitly does not return (volume, reputation, resolution surfaces, prices), which routes agents to the correct sibling for those surfaces.

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