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

The description goes beyond annotations (which don't indicate paid or two-call behavior) to disclose the full payment flow: call without signature to get challenge, sign accepts[0], retry with signature; it explains probe pricing, non-refundable fees, no charge if fresh run cannot be produced, and that probe responses are truncated and never verbatim. It also warns to read amount from accepts[0].amount. No contradictions with annotations.

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 description is dense and thorough, front-loading the core purpose and payment flow. It earns its length by covering substantive caveats (pricing, refund, probe truncation). A slight deduction because the description is very long and repeats the $0.25 fee and 'never charged for nothing' concepts in a slightly redundant way, but every sentence adds important security or usage detail.

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?

The description is complete: it explains the required two-call protocol, how to compute the correct amount, what happens with probes, fee consequences, error/refund behavior, and the report contains probe_report. Given there is no output schema, the description fully compensates by describing what is returned (report, probe_report, verdict, truncated extracts) and what is never returned (verbatim body).

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?

The schema already covers all 4 parameters with high coverage, and the description adds critical semantic meaning for the key 'payment_signature_b64' parameter (omit on first call, set on retry), the 'probe' object's behavior (pricing, ignored when not armed), and the 'services' array (1-8, found via siblings). It explains the exact relationship between parameters and the two-call flow.

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 clearly states the tool performs a paid assessment of service slugs against a user's need, and explicitly distinguishes it from sibling tools search (find services) and get (read cached assessment). It specifies a paid action with a $0.25 USDC fee and a two-call challenge/response flow.

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?

The description explicitly tells the agent when to call this tool: when free signals are exhausted and choosing wrong costs more than a quarter, and it contrasts with x402_search_services and x402_find_best_service, and references x402_get_service for already-computed assessments, giving clear alternatives and conditions.

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?

Matches the readOnlyHint annotation with 'Free and read-only' and adds important caveats beyond the annotation: prices are atomic token amounts not dollars, and payTo values are masked (only change is reported, not the address).

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 description is a single run-on sentence with colon-separated lists, making it a bit dense, but it packs all essential details without redundancy. Could be split into clearer sentences.

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, so the description compensates by mentioning the return shape (most recent first, event types, full snapshots). It could be more explicit about the exact output fields, but the 'before/after envelope snapshots' hint provides enough context.

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?

All five parameters have schema descriptions, and the description enriches them: the type enum is explained with concrete meanings, service is tied to the same slug as x402_get_service, and per_page notes that large pages are heavy due to full before/after snapshots.

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?

Clearly identifies the resource (service change events) and the action (returns a log of payTo, price, and schema changes), with specific triggers for when to call it. Distinguished from siblings by being the change-feed tool rather than search/get/health.

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 scenarios: before trusting cached service data and after a payment failure. Does not explicitly name alternatives, but the two use cases make the intended context clear.

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?

The annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real value by stating 'No money fields' (meaningful in a payment protocol) and enumerating what each mode returns, but it does not disclose rate limits, auth requirements, or how large the include_services=true payload could be.

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 compact and front-loads the when-to-call guidance before the mode breakdown. The telegraphic fragment style ('is this service up right now') is dense but every clause conveys distinct information about inputs or outputs.

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 carries the return-value burden and does so for both modes, listing status counts, uptime windows, response time, consecutive failures, and daily snapshots. The main gap is the lack of any mention of pagination or size limits when include_services=true attaches every row.

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, but the description goes beyond the schema by explaining the slug/no-slug mode split and explicitly tying include_services=true to attaching 'every row'. It adds the operational meaning of the parameters rather than restating them.

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 states a specific purpose (is this service up right now) and clearly separates its two modes: directory snapshot with five status counts versus single-service status with uptime windows. It distinguishes itself functionally by noting 'No money fields', though it never names sibling tools like x402_get_service or x402_assess_services to sharpen the boundary.

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 gives explicit triggering conditions: 'Call this before you send a payment, or right after a call unexpectedly failed.' That is clear when-to-use context, but there are no exclusions or named alternatives, so the agent must infer why this differs from x402_get_service or x402_assess_services.

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 mark readOnlyHint=true, so the description isn't required to state that. However, it adds substantial behavioral detail: the on-chain verification flag, the meaning of 'listed' vs 'on-chain', the exact definition of *_24h fields (today UTC so far, not trailing 24h), and that volume is decimal USD. No contradiction with annotations.

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 description is front-loaded with the trigger condition, then the return payload, then optional features, then caveats — a logical flow. Every sentence carries information; the caveats are essential and not redundant. It's longer than a single sentence but earns its length.

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 read-only data tool with no output schema, the description covers the key output elements (volume, counts, verification flag, timeframes), the units, the optional breakdowns, and the critical temporal caveat. An agent has enough to invoke it correctly and interpret results. Nothing crucial 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?

Schema covers 67% of parameters (4 of 6 have descriptions). The description reinforces include_timeseries and include_chains by calling out 'optional daily timeseries (up to 90 days) and per-chain breakdown', and it reiterates the critical timeframe nuance ('prefer 7d'). While page/per_page lack descriptions in both, they are conventional pagination parameters. The description adds meaningful clarification beyond the schema for the most important params.

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 opens with a precise trigger condition — 'question is about the rail rather than the service' — and names the exact resource (facilitator settlement volumes) and the data returned (volume and tx counts per facilitator). This clearly separates it from sibling tools like x402_search_services or x402_get_service, which target services.

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 explicitly states when to call ('about the rail rather than the service') and what not to do ('never per-service'), plus a strong caveat to prefer 7d over 24h due to reset semantics. While it doesn't name specific alternatives, the per-service/per-facilitator distinction is sufficient routing guidance.

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 and openWorldHint, and the description does not contradict them. The description adds details on ranking methodology but does not explicitly mention that the tool makes no modifications or that results may change (open-world). Given the annotations cover the key behavioral aspects, a neutral score is appropriate.

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 description is unusually long and repetitive, with multiple sentences restating ranking weights and output fields. It lacks a clear front-loaded summary; the first sentence is confusing and the subsequent paragraphs ramble. A concise version would improve readability without losing essential 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?

Given the absence of an output schema, the description attempts to describe the response structure (ranking_version, need_blind_ranking, units map) and the meaning of include_facilitator_context. However, it leaves ambiguities (e.g., what 'units map' keys are, how caveats apply) and does not fully compensate for the lack of a formal output schema.

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?

The schema already provides complete descriptions for all 8 parameters. The description adds context on ranking criteria and mentions some parameters indirectly (e.g., 'price cap' for max_price_usd), but it does not meaningfully enhance parameter understanding beyond the schema. The addition of the 'units map' is unclear and could be considered more about output than input semantics.

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 clarifies that this tool returns ranked service recommendations based on a free-text need and optional filters, distinguishing it from a simple search. However, the phrase 'free ranking step' is ambiguous (likely 'first ranking step' or 'the ranking step'), and the long sentence structure initially obscures the core purpose.

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?

The description gives a broad trigger ('when you have a need in words') but does not explicitly compare with sibling tools (e.g., when to use x402_search_services vs. x402_find_best_service). No 'use X instead' guidance is provided, leaving the agent to infer the tool's relationship to others.

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?

The readOnlyHint and openWorldHint annotations already cover the read-only nature, and the description adds meaningful behavioral detail beyond that, such as the optional include_series behavior and the important units-map warning that prices are atomic token units, not dollars.

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 description is compact and front-loaded with the purpose and use case. It lists response contents efficiently and keeps the optional-series explanation brief, though the phrasing is slightly awkward in places.

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 provided, the description supplies a useful inventory of the response fields and flags the key units caveat. It is sufficient for an agent to understand what it will receive, though 'assessment block' is mentioned without explanation.

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 restates what the schema already explains for slug and include_series without adding significant new meaning beyond the schema text itself.

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 clearly states the action: retrieve the full service record for a given slug, and it lists the key contents (status, uptime, response time, networks, endpoints, assessment). It also frames the intended moment of use ('once you hold a slug and are deciding whether to commit'), which differentiates it from search or health-check siblings.

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?

The description tells the agent when to call it: after obtaining a slug and before committing to a service. It implies this is the comprehensive lookup rather than a lighter health check, though it does not explicitly contrast with x402_check_health or x402_find_best_service.

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 and openWorldHint, so safety is covered. The description adds genuinely useful behavioral context beyond that: result-payload shape (compact summaries, price in decimal USD, uptime, status, verification) and the one-page-of-up-to-100 boundary. It stops short of rate limits or server-side filtering cost caveats that the schema's 'per_page' note hints at.

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 sentences, front-loaded with the routing instruction that matters most. The middle sentence is dense with filter/sort enumeration that largely duplicates the schema, costing a little against pure conciseness.

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 10 params, no output schema, and a directory-scale read, the description covers the essentials: trigger, filter/sort axes, response granularity and size, and the escalation path to the detail tool. Minor gaps are pagination mechanics and how it relates to the sibling ranking/assessment tools.

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% and every parameter carries its own detailed description, including the nuanced signable semantics. The description only restates the filter dimensions (query, category, network, status, signable) and sort orders in prose, adding no syntax or format information 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 ('narrows the directory of listed services to candidates') and frames itself as the discovery entry point. It explicitly distinguishes itself from the sibling x402_get_service, whose job is the full record, so an agent can route without opening a 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?

The opening clause gives a clear trigger condition ('Your first call when you do not know which x402 service exists for a job') and names the follow-up alternative x402_get_service. It does not address when to prefer x402_find_best_service or x402_assess_services instead, so the guidance is strong but not exhaustive.

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