PayAPI Market

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real behavioral context: it is free and spends nothing, it returns the listing regardless of verification status and reports payment_verified honestly, and it explains that reliability is a running score that is not a guarantee. That pre-empts exactly the misinterpretations an agent would otherwise make from the field names.

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?

Purpose is front-loaded, but the middle is repetitive: 'not the per-call price', 'not the price', and 'The per-call price is price_min and price_max' make the same disambiguation three times. The reliability explanation is long for what it delivers, and the docs URL trails at the end where it is least useful.

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 properly carries the return-value burden, covering verification fields, pricing fields, and the reliability object's score/band/computed_at. It stops short of describing not-found or error behavior, which is the main remaining gap for a single-record lookup.

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?

Single parameter with 100% schema description coverage, so the schema already carries the meaning of 'id'. The description's 'by its id or slug' restates the schema rather than adding format or lookup semantics, which is the expected baseline when the schema does the work.

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 and resource: fetch a single live listing by id or slug, with an enumeration of what comes back (base_url, price range, network, verification state). 'Single' implicitly contrasts with the list/search siblings, but no sibling is named 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 is only implied – you call this when you already have an id or slug, and the schema note points at search_apis/list_apis as the id source. There is no explicit when-to-use / when-not statement, and no guidance on what to do when the id is unknown or the listing is absent.

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/openWorld/destructive=false, yet the description adds genuinely new information: the tool is free and spends nothing, and by default only settlement-verified listings are returned unless verified_only is false. That default-behavior disclosure is beyond both the annotations and the bare schema default.

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?

Three short sentences, each carrying a distinct fact (scope, filter behavior, cost/safety). Front-loaded with the primary action and zero filler.

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 four-parameter, no-required-arg list tool with no output schema, the description covers the selection semantics an agent needs. The only gap is pagination/limit handling, which is undocumented in both the schema and the description.

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%: network and category are described in-schema, while limit and verified_only are not. The description partially compensates by explaining verified_only's effect and the category-omission behavior, but says nothing about limit or paging. Baseline 3 for mid coverage.

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 and resource ('Browse the live catalogue') plus the optional scoping dimension (one category). It is clearly a listing tool, but it never distinguishes itself from the sibling search_apis, which an agent could easily confuse it with.

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?

'Omit category for everything' and 'unless verified_only is false' give implied usage for the filters, but there is no guidance on when to pick this over search_apis or get_api. The agent must infer the boundary itself.

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 cover readOnly/idempotent/non-destructive, but the description adds genuinely new context: that results are restricted to settlement-verified listings by default, and that the call is free ('spends nothing') — meaningful in a paid API catalogue. It stops short of disclosing result ordering, pagination, or how the limit interacts with total matches.

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?

Three tight sentences, front-loaded with the core action, followed by match scope and then the default filter. No filler; every clause carries information.

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?

No output schema exists, yet the description conveys what matches, what is filtered by default, and the cost profile — enough to call it correctly. It omits any indication of result shape or paging, which is the only notable gap for a search tool.

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 75%, with query, network and verified_only all self-documented in the schema. The description restates the verified_only default behavior but adds nothing for limit or network (e.g. CAIP-2 handling), so it does not meaningfully exceed the 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?

States a specific verb and resource ('Free-text search across the live catalogue') and enumerates exactly which fields are matched (name, description, category, provider). It is clearly distinguishable from get_api, though it never names list_apis as the non-search alternative.

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 'free-text search' and the mention of the verified_only default, but there is no explicit when-to-use guidance and no routing to list_apis for unfiltered browsing or get_api for detail retrieval. The agent must infer the boundary from the siblings' names.

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?

Discloses behavior an agent cannot infer from annotations: real paid probes up to $0.10 USDC on Base, per-route probing with listed/pending/rejected outcomes, dedupe that returns the existing listing id without creating a second row, and hard rate limits (10/hr per wallet and per email, 50/day per IP and per payTo, applied per element inside urls). The non-live, non-verified boundary is stated explicitly. Minor tension with idempotentHint=false (duplicate submits are described as side-effect-free for the same wallet/API pair), but the description's disclosure is richer than the annotation, not contrary to it.

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?

Front-loaded with the minimum viable input set before the edge cases, which is the right ordering for a 21-parameter tool. It runs long and repeats the 'read from the HTTP 402 when you omit them' idea that the schema already states per-field, and the quoted duplicate-submission message is more verbosity than the agent needs. Still, nearly every sentence carries operational weight.

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 21-parameter mutation with no output schema, the description covers the full contract: required inputs, derivable defaults, probe outcomes and their status vocabulary, cost exposure, rate limits, dedupe behavior, and the update-while-pending path. An agent could call this correctly and set expectations without opening any other artifact.

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 earns extra by adding cross-field semantics the schema cannot express - that contact_email is the only schema-required field yet a paid route (url, paid_route_url, or urls) is also mandatory, that email is an alias, that urls caps at 20, and which fields are recovered from the 402 when omitted. Defaults for category and the rejection of placeholder examples are also clarified.

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 title plus opening line 'List one or more APIs' identifies a marketplace submission, and the body makes clear it probes routes and creates/reuses a listing. The verb 'List' is unfortunately identical to the sibling list_apis, so an agent skimming the first sentence alone could misread the intent. The remainder of the description resolves this, but sibling differentiation isn't stated explicitly.

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?

Gives concrete entry criteria (minimum is a paid URL plus contact_email, email is an accepted alias), explains what can be omitted because it is re-derived from the 402, and states the 'NEVER makes the listing live' boundary. It also covers the resubmission path (same wallet + same API returns the existing id). What's missing is any pointer to siblings such as search_apis for checking whether an API is already listed.

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