paidfor

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

Annotations already declare read-only, idempotent, non-destructive and open-world, and the description goes further by disclosing the verdict taxonomy (avoid/caution/ok/unknown), the statistical payload with its 95% interval, and the presence of evidence links. Since no output schema exists, this return-value disclosure is doing real work an agent needs.

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?

It is a single front-loaded sentence that opens with the usage trigger, which is the right priority. The return-value list makes it long and slightly run-on, but 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?

For a one-parameter read-only lookup, the description covers the trigger, the parameter shape via schema, the safety profile via annotations, and the full return contents. Nothing an agent needs to decide whether and how to call it is missing.

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?

There is a single required parameter with 100% schema coverage, and the schema itself explains that it accepts either a full x402 resource URL or a bare seller domain. The description adds nothing beyond that, so the baseline 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?

The description pairs a specific verb ('check') with a precise resource ('x402 seller') and enumerates what is returned (verdict, paid-call count, failure rate, price, max overcharge ratio, evidence links). Scope is unambiguous, but it never contrasts itself with the sibling list_reliable_sellers or recent_changes, so the agent must infer the split.

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?

Three concrete triggers are given: before any x402 payment, after an HTTP 402 response on retry, and when the user is about to buy an API call with USDC on Base or names a per-call API. That is unusually clear context, though no when-not condition or explicit alternative is named.

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 the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds substantive behavior: the reliability threshold (≥30 paid calls, zero failures) and result ordering (most-called first). It stops short of describing the seller record fields or result-set size handling.

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 sentence with no filler, front-loaded with the usage trigger and followed by the return criteria. Every clause carries information an agent needs.

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 annotations covering safety, schema covering both params, and no output schema, the description supplies the necessary return semantics (reliability definition and ordering). It lacks detail on what a seller record contains, a minor gap given the tool is a discovery/list operation.

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% with only two optional params, and the schema documents both limit and category including the enum values. The description repeats the category options and adds that the filter is optional, but contributes no format or semantics beyond the schema, so baseline 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 (List) and resource (reliable x402 sellers) and operationalizes 'reliable' with concrete criteria: zero failures across at least 30 paid calls. The scope and ordering (most-called first) let an agent distinguish this from check_x402_seller, which evaluates a single seller.

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?

Opens with an explicit trigger: 'Call this when choosing among sellers for a task, or when the user asks for a safe or reliable API.' Clear context for use, though it does not name sibling alternatives or state when not to use it.

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 read-only, idempotent, non-destructive, open-world, so the description's job is the extra context it does supply: result ordering (newest first) and the full inventory of event types, including the notable case where an operator-reported series disagrees with ours. It does not mention result caps or pagination, which for an open-ended 'recent' feed is the one meaningful gap.

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-loads the when-to-use clause before the return inventory, and every clause carries content. The change-type list is long and comma-dense in a single sentence, which costs some scannability but nothing is padded or redundant.

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 return shape — and it does so thoroughly by enumerating the change categories and ordering. It is only slightly short of complete because volume limits and whether 'since' defaults to a window are left unstated.

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% with both properties already documented including the ISO 8601 format and the bare-domain example. The description only restates that host is a filter and since is 'ISO time', adding no semantics beyond the schema, so baseline 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 and resource ('Returns recent changes, newest first') and then enumerates the exact change categories returned — verdict changes, new failures, moved quotes, pay-to changes, new sellers, seller replies, operator-series drift. This enumeration makes it unmistakable against check_x402_seller (single verdict) and list_reliable_sellers (a ranking 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?

Gives two concrete trigger conditions: when the user asks what changed, and as a staleness guard before trusting a verdict older than a day. That second clause implicitly routes to check_x402_seller without naming it, and no when-not guidance is given, so it falls 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.