OmniProvider

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

Annotations already declare this a read-only, idempotent, open-world operation, so safety is covered. The description adds genuine behavioral detail on top: the two pricing modes (fixed per-call vs. per-token), the conditional cost estimate when a model and token counts are supplied, and the minimum charge per rail. It omits auth/rate-limit or error behavior, but for a read-only lookup this is solid.

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 dense sentences with no filler, and the core return content leads. The jargon ('routes', 'rails', 'brief') is compressed to the point of mild ambiguity, which slightly undercuts the structure.

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?

There is no output schema, so the description must convey the return shape, and it mostly does (price fields, optional estimate, minimum charge per rail). It leaves unresolved what an all-defaults call returns, what 'routes' and 'rails' denote, and how it differs from omniprovider_get_quote — gaps that matter for a 3-param tool with zero required inputs.

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 only 33% (just `model` is documented), so the description carries extra burden. It partially compensates by explaining that `model` plus input/output token counts together unlock the estimated cost, but it never clarifies token units/counting, whether the two token params are meant to be used together, or limits beyond the schema's max values.

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?

It states a specific verb and resource ('Returns prices') and enumerates what pricing data is available: fixed per-call prices for the nano/small/brief routes and per-token catalog prices. That is well beyond a restatement of the name. It does not, however, distinguish itself from sibling omniprovider_get_quote, which plausibly also returns cost figures.

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 is only implied: the agent can infer that supplying a model plus token counts triggers a cost estimate, while omitting them yields raw prices. There is no explicit when-to-use, no exclusion conditions, and no routing to omniprovider_get_quote or omniprovider_list_models despite the obvious overlap.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely new behavioral context: it performs a real network call to the paid route, returns a 402 challenge, makes no payment, and transmits no credential. Missing are rate-limit behavior and whether the route must be reachable/valid.

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 tightly packed sentences, front-loaded with what the tool does and its return payload, then the safety guarantee and scoping constraint. No filler, no repetition of the title or 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, the description correctly compensates by enumerating the returned 402 fields (amount, currency, network, payee, protocol). Combined with the 100%-covered schema and read-only annotations, an agent has nearly everything needed; only edge behavior (invalid route, rate limits, whether any auth is ever required) is unaddressed.

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% for both parameters (route enum with MPP vs x402 note, body contents), so the schema carries the load. The description only reinforces that the body determines the quote ('that exact request body') without adding format or constraint detail beyond the schema, which matches the baseline 3.

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 ('sends one unpaid request to a paid route and returns the 402 payment requirements') and even enumerates the returned fields, so an agent knows exactly what it produces. It does not name or contrast itself with siblings like omniprovider_get_pricing, though the 'quote for that exact request body' phrasing implicitly separates it from a static price 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?

Usage is implied: this is the pre-flight step to discover payment terms before paying. The description clarifies that no payment or credential is sent, which signals it is safe to call speculatively, but it never states when to prefer this over omniprovider_get_pricing or omniprovider_how_to_pay, and gives no exclusions.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior, so the safety profile is covered. The description adds genuinely new context beyond that: payment is produced by the caller's own wallet tooling and 'this server holds no keys', which clarifies the trust model and division of responsibility.

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 tight sentences that front-load what is returned and then add the key architectural caveat. No filler, and every clause earns its place.

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 low-complexity, single-optional-parameter read tool with no output schema, the description fully covers the return payload and the caller's responsibility. An agent has everything needed to call it and interpret the result.

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?

With 100% schema description coverage, the schema already documents the 'rail' enum and its 'all rails when omitted' default. The description only references 'for a rail' generically and adds no syntax or behavioral detail beyond the schema, so the baseline of 3 applies.

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?

States a specific verb ('Returns') and resource ('the payment flow for a rail') and enumerates exactly what comes back: endpoint URL, required headers, nonce format, and client commands. This is clearly distinguishable from siblings like get_pricing and get_quote, which return data rather than integration instructions.

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 is implied by the name and content (call it when you need to know how to construct a payment), but the description never states when to use this versus get_quote or get_pricing, nor any prerequisites. No explicit when/when-not or alternative routing is given.

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

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description usefully discloses the return payload contents (ids, context windows, token limits, prices, payment rails), but adds nothing about auth needs, rate limits, or pagination.

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?

A single front-loaded sentence with no filler; the field enumeration earns its space because there is no output schema. Slightly dense but efficiently structured.

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, describing the returned fields is the right call and it does so. The remaining gap is routing guidance against the pricing siblings and any mention of the tier filter's effect, but for a simple read-only catalog listing this is close to complete.

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?

Only one parameter (tier) with 100% schema description coverage and an enum, so the schema fully documents it. The description never mentions the tier filter or what 'open' vs 'frontier' means, so it adds no meaning beyond the schema — baseline 3.

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?

States a specific verb ('Returns') and resource ('the public catalog') and enumerates the fields returned, so the agent knows exactly what this produces. It does not, however, distinguish itself from siblings like omniprovider_get_pricing, which appears to overlap on price information.

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?

There is no when-to-use or when-not-to-use guidance, and no sibling is named. The agent must guess whether to call this or omniprovider_get_pricing / omniprovider_get_quote for pricing, since the description itself advertises price data.

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