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

Annotations already declare readOnlyHint and openWorldHint, but the description adds real behavioral context beyond them: it confirms 'Never executes', explains that missing figures return null with a reason, enumerates the Rate Receipt schema fields and its three status values, and discloses a tiering behavior (free callers see Route A/B, a router key sees source names). Rate limits and caching lifetime details are not given, only a pointer to max_age_seconds.

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 purpose is front-loaded in the first clause and the remaining sentences each carry distinct payload (receipt fields, refresh signal, null behavior, access tiering, non-execution). The Rate Receipt field enumeration is long but earns its place since no output schema exists; minor density cost from packing everything into one paragraph.

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 no annotations covering return shape, the description correctly compensates by naming the receipt schema and its fields and statuses, and by explaining null-plus-reason for missing figures. What remains thin is the relationship to the numerous sibling rate tools and any guidance on error or auth-failure behavior.

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 description coverage is 100%, so all five parameters are already documented, and the description mostly restates them ('amount at a payment size', corridor, access_key). The only added meaning is that amount represents the pricing size and that a router key changes the granularity of source names, which is useful but marginal against a fully documented schema.

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 gives a specific verb and resource ('Read public prices for a corridor at a payment size') and scopes the data sources (on-chain pools, public order books, public adverts) plus the access constraint ('no partner key'). That implicitly separates it from keyed or execution-oriented siblings, but it never names an alternative such as get_corridor_rates or assess_route, so the differentiation is left to inference.

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?

Usage context is implied rather than stated: 'with no partner key' and 'Never executes' tell the agent this is a read-only, unauthenticated pricing call, and 'max_age_seconds says when to read again' hints at refresh behavior. There is no explicit when-to-use or when-not-to-use versus the many rate-related siblings, and no stated prerequisites for obtaining a router key.

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