Novarithm Agent Hub: SEO & GEO audits and business checks

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

With no annotations, the description carries the burden and does disclose important behavior: it is a paid x402 call at $0.01 USDC on eip155:8453, and it validates fields, skills, interfaces, auth, signature, and reachability. It stops short of explicitly stating read-only/no-side-effects, timeout behavior, or rate limits.

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: payment metadata, core action, validation scope, and output summary all appear without filler. Every clause contributes to selecting or using the tool.

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 validation tool with no output schema, the description is largely complete: it names the card versions, validation dimensions, and the 0-100 score plus issues result. It could be slightly more complete by explicitly stating read-only behavior and what the issues output contains.

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 single required parameter is fully documented in the schema, including that it accepts a base/domain URL or direct card URL. The description does not add parameter syntax or edge-case meaning beyond the schema, so the baseline of 3 is appropriate.

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 uses a specific verb and resource: 'Fetch and validate a peer agent's A2A Agent Card (v1.0 / v0.3)'. It also enumerates the validated aspects and the output, making it clearly distinguishable from siblings like mcp_probe or x402_probe.

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 implies the tool is for checking A2A Agent Cards, but gives no explicit when-to-use guidance, prerequisites, exclusions, or alternatives. An agent must infer when this is preferable to sibling probing or verification tools.

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?

With no annotations, the description carries the full burden and does well: it discloses the x402 pay-per-call model at $0.01 USDC on eip155:8453 (critical for an agent that must handle payment) and states the return shape (A-F grade plus concrete fixes). It stops short of noting rate limits, failure behavior for malformed/URL input, or whether the payment is charged on error.

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 compact clauses: the price/mechanism prefix followed immediately by the capability and the checks performed. Nothing is wasted, though the parenthetical payment metadata is dense enough that a reader must parse it before reaching the actual purpose.

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 single-argument read tool with no output schema, the description covers what is inspected and what comes back (graded result with fixes), which is enough to decide and invoke. Missing only minor operational details such as per-call latency and behavior on invalid input.

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 only one parameter and schema description coverage is 100% ('Domain, e.g. example.com (URL accepted)'), so the schema already fully specifies it. The description adds nothing about the domain argument beyond restating that a domain is the target — 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+resource ('Audit a domain's email authentication') and enumerates the exact record types checked (MX, SPF, DMARC, DKIM, MTA-STS, TLS-RPT, BIMI, domain age). This clearly separates it from sibling email_check, which is a mailbox-level tool rather than a domain-wide authentication audit.

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 domain-audit framing implies when to reach for it, but there is no explicit routing guidance against alternatives like email_check, gtin_recall, or the seo_* family. No prerequisites, exclusions, or 'use X instead when...' statements are offered.

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?

With no annotations, the description carries the full burden and does well: it discloses the price/mechanism ($0.003 USDC/call via x402 on eip155:8453) and that no mail is sent, i.e. no side effects. It omits rate limits, latency, and whether repeat calls are charged, so not a 5.

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?

One dense sentence with zero waste, but the pricing bracket is front-loaded ahead of the actual purpose. Moving the verb first would have let the agent classify the tool faster.

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, no-output-schema tool, the description is nearly sufficient: it enumerates the checks performed and the four return classifications with a score, and it discloses the paid model. Only the meaning/scale of the score and any pagination-free guarantee are left implicit.

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% and the single 'email' parameter is fully documented in the schema. The description only reinforces 'one email address' and adds no format, normalization, or validation detail beyond the schema, so the 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 ('Validate one email address') plus the negative constraint 'without sending mail', which sharply bounds the operation. It does not name the nearby siblings (domain_email_health, evaluate_deliverable) to route the agent, so a 4 rather than a 5.

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 'one email address' and 'without sending mail', which quietly excludes bulk/domain-level validation. There is no explicit when-to-use, no exclusion, and no pointer to the sibling that handles domain-level health, so the agent must infer the boundary.

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?

With no annotations, the description carries the burden and discloses important behavior: paid $0.25 USDC/call via x402, eip155:8453, return verdict/score/criteria, signed EIP-712 attestation, ERC-8183 reason digest, and no funds held. It still does not fully describe operational details such as URL-fetch security, idempotency, or failure behavior.

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 but efficient, front-loading pricing/rail context before the core purpose and output details. It avoids fluff, though the single long sentence is somewhat packed and could be easier to scan if 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?

For a six-parameter tool with no output schema, the description does a good job naming the return fields and explaining the attestation and payment context. It is mostly complete, though it does not cover error cases, attestation storage, or full output structure.

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 six parameters are already documented in the schema. The description adds context about deliverable/spec formats and attestation output, but does not add parameter-level meaning beyond what the schema provides.

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: evaluate a deliverable against a job spec. It also lists the concrete outputs (verdict, score, checked criteria, signed EIP-712 attestation), so the agent can distinguish this from generic verification or payment tools.

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 implies usage by stating that it evaluates a deliverable against a job spec, but it does not explicitly say when to use this versus alternatives such as verify_attestation or other sibling tools. No when-not conditions or alternative-routing guidance are provided.

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?

With no annotations, the description carries the full burden and does meaningful work: it discloses the paid x402 model, price ($0.002 USDC/call), network (eip155:8453), and the shape of the response. It does not say what happens for weekends/holidays or unsupported currency pairs, which for a rate lookup is the main remaining behavioral 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?

Two compact clauses with the payment/auth requirement front-loaded, then purpose, scope and return values. No filler; every clause carries distinct 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, and the description compensates by naming the returned fields (rate, amount, rate date). Combined with full schema coverage and the pricing disclosure, an agent has enough to call it correctly; only edge-case behavior (missing fixing dates, unsupported pairs) is 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 description coverage is 100%, so the schema already documents from/to/date/amount including defaults. The description adds only the outer date bound (1999) and mentions CFA franc and Gulf pegs, which hints at currency coverage beyond the ISO examples but does not define parameter behavior beyond 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: 'Convert an amount between two currencies at the official ECB reference rate.' The scope ('today or any date since 1999') and the return payload ('rate, amount, rate date') let an agent distinguish it from fx_latest (single latest rate) and fx_timeseries 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 date-range scope implies when this tool applies versus fx_latest and fx_timeseries, but no alternative is named and there is no explicit when-not guidance. An agent must infer the routing from the sibling names alone.

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?

With no annotations, the description carries the behavioral burden and discloses important traits: the tool is paid ($0.002 USDC/call), uses x402 on eip155:8453, and returns a full rate table in one call. It does not cover rate limits, error behavior, or response structure in detail, but the payment and output-scope context are substantial beyond the schema.

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-loads the payment metadata before the core purpose. Every phrase contributes useful information: cost, protocol, chain, scope, supported pegged currencies, and the one-call full-table behavior. There is no redundant or filler text.

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, three-parameter rate retrieval tool with full schema coverage, the description is mostly complete. It covers payment requirements, base/date scope, pegged currencies, and the full-table output, though it does not describe the exact response format even though no output schema exists.

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 the baseline is 3. The description references the key concepts behind the parameters—'any base currency,' 'latest or a given fixing date,' and 'full rate table'—and adds that pegged currencies are included, but it does not add syntax or filtering details beyond what the schema already provides.

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 resource and scope: all official ECB reference rates for a base currency on the latest or a given fixing date. It also notes that pegged currencies are included and that one call returns the full rate table. It does not explicitly name sibling alternatives like fx_convert or fx_timeseries, so it is clear but lacks sibling differentiation.

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 through phrases like 'latest or a given fixing date' and 'One call, full rate table,' which suggest retrieving a complete rate snapshot rather than performing a conversion. However, there is no explicit when-to-use guidance, no exclusions, and no named alternative tools for cases such as conversion or time-series requests.

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?

With no annotations, the description carries the full burden and delivers key facts: it is a paid call ($0.005 USDC, x402, eip155:8453) and returns derived statistics plus % change. It omits auth mechanics beyond the payment hint and pagination/error behavior, but the pricing disclosure is substantive context an agent would otherwise lack.

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 compact sentences, with pricing front-loaded and the resource/scope statement immediately following. Every clause contributes; only the parenthetical pricing block is dense but justified.

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 naming the returned aggregates (min, max, mean, % change). Combined with the pricing and date-window disclosure, an agent has enough to call it correctly; only error/empty-range behavior 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 coverage is 100%, so all four parameters are documented in the schema (from/to ISO 4217, start/end dates with defaults). The description only adds the 366-day cap and the pair concept, which maps to the schema's start/end semantics but adds no syntax beyond it. Baseline 3 is appropriate.

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 resource (daily official ECB exchange rates for a currency pair) with scope (up to 366 days) and output content (min, max, mean, % change). Clearly distinguishable from fx_latest/fx_convert by the timeseries framing, but does not name those siblings 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?

Offers use-case hints (invoicing, hedging checks, reporting) that imply when this tool fits, but never states when to prefer it over fx_latest or fx_convert, nor names alternatives. Usage is implied rather than explicit.

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?

No annotations, so the description carries the burden and it does well: it discloses the paid execution model ($0.02 USDC/call, x402, eip155:8453) and the return shape ('Score + ranked fixes'). It omits rate limits/permissions, but the payment and output context is substantial value beyond any structured field.

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?

Dense but front-loaded: pricing/payment lead, then the audit scope, then the return. Every clause carries information; it could be marginally better structured but there is no waste.

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, one-param audit with no output schema, the description covers payment model, the signal categories checked, and the return format (score + ranked fixes), which is enough for an agent to call it. Minor gap is the lack of explicit routing against SEO siblings.

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% and the single url parameter is fully documented in the schema (page URL or domain with example). The description adds nothing beyond that, so baseline 3 is correct.

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+resource: a 'GEO audit' of whether AI assistants (ChatGPT, Claude, Perplexity, Gemini) can cite a site. The AI-citability angle distinguishes it from the SEO siblings (seo_full_audit, seo_technical_audit), though it doesn't name those siblings 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?

Usage is implied (audit a site for AI-search visibility) but there is no explicit when-to-use/when-not or comparison against the many seo_* alternatives that overlap. An agent must infer the GEO-vs-SEO 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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the call costs $0.01 USDC via x402 on eip155:8453 and that the check digit is validated, but it omits what is returned, what happens when no recall is found or the check digit fails, and any rate-limit or auth detail beyond payment.

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?

One compact sentence front-loads the payment cost and then states the purpose and sources. It is efficient, though the paid-call prefix competes with the core purpose for the agent's first attention.

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 paid, one-parameter lookup with no annotations and no output schema, the description covers cost, protocol, source coverage and input validation. It is still missing the shape of the result and the behavior on invalid or unmatched barcodes, and it does not clarify how it differs from recall_search.

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 the schema already documents the gtin parameter as an 8/12/13/14-digit barcode with an example. The description adds only that the check digit is validated and that exactly one barcode is checked, so the baseline 3 is appropriate.

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: 'Exact recall check' for a single EAN/UPC/GTIN barcode, and names the three data sources. It implies a precise barcode lookup rather than a keyword search, but it never names the sibling recall_search tool, so the distinction must be inferred.

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 phrase 'Exact recall check for one ... barcode' implies the tool is for single-barcode verification, which suggests when to use it. However, there is no explicit when-to-use, when-not-to-use, or comparison against recall_search or pre_purchase_check, leaving the agent to guess.

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?

With no annotations, the description carries the burden and discloses key behavior: it is paid at $0.01 USDC/call via x402 on eip155:8453, performs a handshake, and explicitly does not make a tool call. It still omits rate limits, error behavior, and whether payment must be settled before the handshake, but the main behavioral traits are covered.

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, dense sentence that front-loads payment metadata and then states the operation and return details. It is efficient and contains no filler, though the bracketed payment prefix makes it slightly less immediately purpose-focused.

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, but the description enumerates the key return values (reachability, protocol version, tools, schemas, latency, OAuth metadata) and covers the payment model. It is mostly complete for an endpoint probe, missing only finer details like timeout behavior or the exact payment flow.

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 only one parameter, and the input schema already documents it fully with an example endpoint. The description adds no additional meaning about the URL parameter, so the high schema coverage sets the baseline at 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 states a specific operation: performing a real MCP Streamable HTTP handshake (initialize + tools/list, no tool call) and returning reachability, protocol version, tools, schemas, latency, and OAuth metadata. It clearly distinguishes its scope from tools that actually invoke MCP tools via the 'no tool call' phrase, though it does not explicitly name sibling alternatives like x402_probe.

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 lists what the probe returns, which implies it is for endpoint inspection, but it provides no explicit when-to-use guidance, no exclusions, and no comparison to sibling tools such as x402_probe. It also does not state prerequisites like payment requirements before invocation.

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?

With no annotations, the description carries the load and discloses cost ($0.08 USDC/call), payment protocol (x402), and chain (eip155:8453) — critical invocation context. It's missing rate-limit, failure-mode, and latency disclosure, but the payment/authorization profile is well covered.

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 dense sentence with zero filler, front-loading the payment cost and then the capability. Slightly packed with parenthetical source lists, but every clause conveys distinct information (cost, sources, output decision).

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 does well to name the decision outputs (proceed/caution/stop) and the signal categories returned. It doesn't describe response shape details like per-signal scores, but an agent can call it correctly and interpret the headline 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?

Schema description coverage is 100%, so all four parameters are documented in the schema itself, including the GTIN-vs-page fallback and the default market. The description adds no parameter-level detail beyond what the schema provides, 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 composite resource: verified price/stock, seller trust, and recall status for a product URL, returning a proceed/caution/stop decision. It is clearly the bundled aggregator over siblings like price_availability, seller_reputation, gtin_recall, and recall_search.

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?

"Bundle before paying" implies the trigger context (just before a purchase), and the proceed/caution/stop framing suggests when the output matters. However, there is no explicit when-not guidance or statement telling the agent to use the narrower siblings when only one signal is needed.

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?

With zero annotations, the description carries the full burden and does so well: it discloses the billed cost ($0.03 USDC/call), the payment protocol and chain (x402, eip155:8453), robots.txt compliance, and the failure contract (blocked or unpriced pages return 'unavailable' and are not charged). Those are exactly the operational facts an agent needs before spending money on a call.

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; every clause carries information (cost, protocol, extraction sources, failure behavior). The billing banner leads ahead of the purpose statement, which is slightly less ideal front-loading, but the purpose is still established in the first sentence.

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, no-output-schema tool with no annotations, the description covers what is returned in substance (price, currency, availability, seller), what sources it reads, and what happens when it cannot price the page. Only minor gaps remain: exact response shape and whether 'unavailable' still bills partially are not spelled out.

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 the single required parameter includes a concrete example URL, so the schema already does the heavy lifting. The description confirms the input is a product page URL but adds no format, normalization, or accepted-domain guidance beyond that. 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?

The description uses a specific verb set (verified price, currency, availability, seller) against a clearly bounded resource (a product page URL), and names the extraction sources (JSON-LD / microdata / OpenGraph). This is far more than a restatement of the name. It falls short of a 5 because it does not distinguish itself from the sibling 'pricing' or 'pre_purchase_check' tools, which plausibly overlap.

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 rather than stated: the tool takes a product page URL and returns verified commercial facts, so an agent can infer it is for product-level price checking. There is no explicit when-to-use/when-not, and no routing to or away from the sibling 'pricing', 'pre_purchase_check', or 'seller_reputation' tools despite 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?

With no annotations, the description does carry useful behavioral weight: it discloses that the call itself is free and that prices are denominated in USDC on Base mainnet. It does not address whether any auth or payment header is needed, how many tools are returned, or the response shape — meaningful gaps for a tool with zero annotation coverage.

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 short clauses, zero filler, with the most decision-relevant fact ('Free') front-loaded. Nothing could be removed without losing 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 trivial zero-parameter, read-only listing tool with no output schema, the description says enough to call it correctly and understand what comes back (tool names plus per-call USDC prices). Only the absence of any return-format or auth expectation keeps it from being fully 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?

The tool takes zero parameters, so there is no parameter semantics to explain; the schema is an empty object. Baseline 4 applies, and nothing in the description misleads about inputs.

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 (lists), a specific resource (every paid tool with its price per call), and adds the payment rail and network (USDC, Base mainnet). An agent can immediately tell this is a price-discovery endpoint and distinguish it from verification siblings like verify_usdc_payment or usdc_balance.

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 leading 'Free.' implicitly signals this is costless to call and therefore the natural first step before invoking any paid sibling, but the description never says so explicitly nor names which siblings are the paid ones. Usage is inferable rather than stated.

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?

With no annotations, the description carries the burden and does disclose the critical behavioral fact that each call costs $0.01 USDC via x402 on eip155:8453 — an agent needs that before invoking. It also scopes the data sources covered, though it omits result shape, pagination and rate-limit behavior.

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 dense sentence with the payment constraint front-loaded in brackets, followed by the action and filters. No filler, though the source list and facets make it slightly packed.

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 search with no output schema and no annotations, the description covers sources, payment requirement and filter dimensions. What remains missing — return fields and pagination beyond the limit param — is modest but real given there is no output schema to fall back on.

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 four parameters are already documented in the schema. The description only echoes the query, market and period facets without adding syntax (e.g. how market values map, or what days=0 means), 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 (search) and resource (official recall notices) and enumerates the data sources (CPSC, openFDA food/drug/device, RappelConso FR). It implies a distinction from the sibling gtin_recall by describing lookup by product/brand/model text rather than GTIN, but never names that sibling 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?

The facets (product/brand/model query, market filter, period) imply when the tool fits, but there is no explicit when-to-use or when-not-to-use guidance. Nothing tells the agent why it should pick this over gtin_recall for a barcode-style lookup.

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?

With no annotations, the description carries the full burden and does well: it discloses the paid x402 mechanism, exact price, and network (eip155:8453), the covered chain families, and the boolean-plus-entity return. It stops short of error behavior for malformed addresses or list-freshness guarantees, which keeps it below a 5.

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 compact sentences with the cost/transport tag front-loaded, then purpose, coverage, and return value. Nothing is redundant and everything is front-loaded for fast scanning.

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 single-parameter lookup with no output schema or annotations, the description covers cost, transport, coverage, and return semantics adequately. It could add one line on invalid-address behavior or how current the OFAC list is, but an agent can call it correctly as written.

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% and only one parameter exists, so the baseline is 3. The description nonetheless adds real meaning: it enumerates the accepted chain families (BTC, ETH/EVM, TRON, LTC, XMR, SOL) that constrain what a valid address string looks like, going beyond the schema's generic '0x… or bc1…' example.

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 (check) and resource (crypto address) plus the exact data source (OFAC SDN digital currency addresses) and the return shape. It is clearly a single-address sanctions lookup, distinguishable from the sibling sanctions_screen by virtue of operating on addresses rather than names/entities.

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 implies when it applies (a crypto address needs sanctions screening) but never says when to prefer it over the sibling sanctions_screen or what to do when the chain is unsupported. The paid-per-call note is useful gating context but not a usage rule.

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?

With no annotations, the description carries the full burden and does disclose the payment mechanism ($0.01 USDC/call, x402, eip155:8453), fuzzy matching with alias handling, and the returned fields — context the schema cannot convey. It is silent on no-match behavior, result truncation/pagination, and what a paid call failure looks like, which matters for a paid mutation-adjacent tool.

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, front-loaded with the paid-access metadata before the capability statement. The bracketed payment prefix is slightly cluttered but carries decision-relevant information rather than 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?

Seven parameters with no output schema, yet the description names the return fields (score, list, programs, countries), covering the biggest gap. Remaining gaps are minor: nothing about empty-result handling or result caps, though max_results in the schema partly covers the latter.

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 the baseline is 3. The description reinforces the multi-list and fuzzy/alias semantics but adds no syntax or format detail beyond what the schema already documents for name, lists, country, threshold, and the boosting fields.

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: screen a person or company name against OFAC SDN, UN, EU and UK sanctions lists. The phrase 'person or company name' implicitly distinguishes it from the sibling sanctions_crypto_address, though it never names that sibling 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?

No explicit when-to-use or when-not guidance and no named alternative. The 'one call' phrasing and the list coverage imply this replaces four single-list lookups, and the cost prefix hints it is a paid endpoint, but the agent must infer all of that.

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?

With no annotations, the description carries the full behavioral burden and does disclose key traits: the $0.02 USDC/x402 payment requirement, the network, and the short JSON return shape with risk, advice, red_flags, and reasons. It stops short of explicitly saying the operation is read-only or describing rate limits.

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 definition is compact and front-loaded: payment terms first, then the score and factors, then return fields. Every clause contributes useful information without waste.

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 tool with no output schema and no annotations, the description is mostly complete: it covers the score range, inspected signals, payment requirement, and returned JSON fields. A bit more on usage constraints or read-only behavior would make it fully self-contained.

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 single domain parameter is already fully documented in the schema. The description reinforces that a domain or URL is accepted but adds no syntax or format detail beyond 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?

The description states a specific output (trust score 0-100) and resource (online store domain or URL), and enumerates the signals used. It is clear, but it does not explicitly distinguish itself from nearby tools such as pre_purchase_check.

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 store-domain focus and trust-score output, but there is no explicit statement of when to use this tool versus alternatives or 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?

With no annotations, the description carries the behavioral burden and does well by disclosing the paid cost ($0.06 USDC/call), payment protocol (x402, eip155:8453), crawl depth (12 pages), and output shape (weighted score, 12 priority actions, module details). It stops short of stating whether the operation is read-only or describing payment preconditions, but the key cost and scope are clear.

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 dense sentence that front-loads the paid-call context and then states the audit scope, crawl depth, and outputs. Every clause carries relevant information without waste.

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 a complex audit tool with no output schema, the description lists the major modules and return elements (score, priority actions, module details), which is enough for an agent to understand what to expect. It could be slightly more complete about output structure or payment flow, but the essential context is present.

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 the single URL parameter is already fully documented in the schema. The description adds no parameter-specific semantics beyond the schema, which is acceptable at the baseline for full 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?

The description states a specific action and resource: a full SEO + GEO audit in one call. It enumerates the covered areas (technical, keywords/content, internal links, local presence, AI visibility) and distinguishes itself from the individual module siblings by emphasizing the combined audit.

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 phrase 'Full SEO + GEO audit in one call' gives clear context for when to use this aggregate tool rather than individual module tools. However, it does not explicitly name the sibling alternatives such as seo_technical_audit or state when not to use this broader/paid audit.

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?

With no annotations, the description carries the full burden and does well: it discloses the paid cost ($0.03 USDC/call, x402, eip155:8453), robots.txt compliance, a 30s time cap, and same-site crawl restriction — real behavioral constraints beyond the schema. It stops short of describing response shape or failure behavior, but the enumerated findings effectively telegraph the output.

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?

One dense sentence with zero filler; the pricing/transport tag is front-loaded and the audit scope follows immediately. The long findings list is justified because each item defines the tool's output, though the sentence runs long and could be lightly 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?

No output schema exists, so the enumerated finding categories serve as an implicit return-value description, and crawl limits plus payment terms are disclosed. What remains thin is the absence of any note on how results are returned or what happens at the 30s cap, but for a 2-parameter read tool 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?

Schema coverage is 100%, so the baseline is 3; the description adds genuine value by tying max_pages to the crawl behavior and pairing it with a 30s cap, which explains why the range is bounded. The url parameter is left to the schema's own undocumented-example description, but that is sufficient.

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+resource ('Internal linking audit: crawls ... pages') and enumerates the exact checks (broken internal links, orphan pages, click depth, dead ends, anchors, nofollow, duplicate titles, missing meta descriptions). This is clearly distinguishable from seo_full_audit or seo_technical_audit by content, though the description never explicitly names those siblings to route the agent away from them.

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 by the enumeration of link-specific checks and the 'same-site pages' crawl scope, so an agent can infer this is the focused internal-linking tool. However, there is no explicit 'use this when... instead use seo_full_audit/technical_audit when...' guidance, and no prerequisites stated beyond the price line.

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?

No annotations are supplied, so the description carries the burden, and it does disclose the critical trait that this is a paid call ($0.01 USDC, x402, eip155:8453) plus what the response contains (score + fixes). It does not cover failure behavior for unreachable pages or payment prerequisites, so it stops short of full disclosure.

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 payment/network tag leads, followed by the capability summary and expected output, so the important facts are front-loaded. The middle is a long comma-chained list, but each item maps to a distinct analysis dimension rather than padding.

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 only two well-documented params and no output schema, the description is nearly self-sufficient: it discloses cost, scope, and result shape. The remaining gap is the absence of any note on input validation or what happens when the URL is not publicly reachable.

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 already 100%, so the baseline is 3, but the description adds real semantics by noting the focus keyword can be 'given or detected' — telling the agent that `target` is optional and that auto-detection occurs when omitted. That is meaning beyond the schema's plain field description.

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: on-page keyword and content analysis, with an enumerated scope (title/H1/meta/first 100 words/URL placement, density, headings, FAQ, readability). This clearly separates it from technical or link-focused siblings like seo_technical_audit and seo_internal_links, though no sibling is named 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?

Usage is implied by the scope list — call it on a single page to check keyword placement and content quality — but there is no explicit statement of when to prefer this over seo_full_audit or seo_technical_audit. 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?

No annotations are provided, so the description carries the burden. It usefully discloses the paid x402 USDC cost/chain and the local signals it inspects, and 'Score + fixes' hints at output, but it does not state read-only/safety behavior, rate limits, failure modes, or detailed return format.

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 dense but informative sentence, front-loading the paid-call notice before enumerating the local-presence checks. It could be more scannable, but every clause adds useful signal.

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 paid SEO report with no output schema, the description covers payment and the kinds of local signals inspected. However, the scoring scale, fix format, and returned data structure are unspecified, leaving meaningful gaps for an agent interpreting 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?

There is one parameter with 100% schema description coverage, and the schema already defines it as a public page URL or domain. The description adds no additional URL constraints or syntax beyond 'from the website', so the schema does the heavy lifting.

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 scope: local SEO/listings readiness signals from a website, including phone, address, JSON-LD, Maps/reviews, social profiles, plus score and fixes. This clearly distinguishes it from generic SEO audit siblings by local-presence focus, though it does not explicitly name those alternatives.

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 'local SEO / listings readiness' and the listed local signals, but there is no explicit when-to-use/when-not guidance or routing versus siblings like seo_full_audit, seo_technical_audit, or seo_keywords_content.

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?

No annotations are provided, so the description carries the behavioral burden and does well: it discloses pricing ($0.02 USDC/call, x402, eip155:8453), the exact audit scope, and that the result includes a 0-100 score plus ranked fixes. It leaves implicit that the operation is read-only, but the audit nature makes that expectation clear.

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 but front-loaded: payment terms first, then purpose, then the checklist, then the output shape. Every clause carries information, though the long unbroken checklist makes it slightly less scannable than it could be.

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 supplies the essential return shape ('Score 0-100 + ranked fixes') and enough scope detail for a one-parameter audit tool. The main missing piece is sibling differentiation, which belongs more to usage guidance than to completeness of the tool's own contract.

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 documents the single url parameter at 100% coverage, including the public page URL or domain example. The description only says it audits 'a URL' and adds no syntax, format, or constraint details beyond what the schema provides, 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 and resource: 'Technical SEO audit of a URL', and enumerates concrete checks, so the purpose is unmistakable. However, it does not distinguish itself from the sibling seo_full_audit, so an agent cannot tell from the description alone which audit to choose.

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 phrase 'Technical SEO audit' implies the appropriate context, and the listed checks imply use for technical issues rather than content or local SEO. But there is no explicit when-to-use guidance and no mention of alternatives such as seo_full_audit, seo_keywords_content, or seo_local_presence.

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?

With no annotations, the description carries the full burden and does well: it discloses the paid x402 flow, the exact price ($0.002 USDC/call), the chain (eip155:8453), the upstream data source, and the no-charge rule for unknown postcodes. It omits whether lookups are cached or rate-limited and what an unknown postcode actually returns, which keeps it short of a 5.

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?

One dense sentence that front-loads the cost/transport tag, then the purpose, then the return surface. Efficient, though the bracketed payment prefix is visually noisy relative to the lookup itself.

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, and the description compensates by enumerating the returned fields (lat/lon, country, region, local authority, ward, constituency, NHS ICB, police force, LSOA). Combined with the payment disclosure, an agent has what it needs to decide and call, though the shape of an unknown-postcode response is left open.

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% and the single parameter already has a format example ('SW1A 2AA'), so the schema does the work. The description adds no normalization rules (spacing, casing, partial postcodes), so baseline 3 is appropriate.

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+resource ('UK postcode lookup') and backs it with the data source (ONS Postcode Directory via postcodes.io) and the exact field set returned. The UK qualifier implicitly separates it from the us_geocode sibling, but the distinction is never made explicit.

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 statement of when to choose this tool over us_geocode or any other geo tool, and no prerequisites. The only conditional language ('Unknown postcode = not charged') is billing behavior, not invocation 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?

With no annotations provided, the description discloses important behavioral context: paid cost of $0.001 USDC per call, x402 protocol, chain identifier eip155:8453, and that the balance is read via balanceOf on the official Circle contract. It does not mention rate limits, failure behavior, or return format, but the payment and data-source disclosures are substantial.

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 compact sentence plus a bracketed payment preamble, with no filler. It front-loads key operational context and states the core purpose immediately afterward.

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 tool is simple and the schema fully documents its two parameters, but there is no output schema and no annotations. The description does not specify the return format or precision of the balance, nor does it describe error or payment failure behavior, which leaves some gaps for a paid financial 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?

Schema description coverage is 100%, so both the address and chain parameters are already documented in the input schema. The description adds no parameter syntax or constraints beyond what the schema provides, making the baseline score of 3 appropriate.

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 resource and result: "Current USDC balance of an address on Base or Base Sepolia." It also identifies the underlying method, balanceOf on the official Circle contract. It does not explicitly distinguish itself from siblings, but the core purpose is clear.

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 explicit guidance on when to use this tool versus siblings such as verify_usdc_payment or sanctions_crypto_address. The description implies usage by saying "Current USDC balance," but it provides no when/when-not criteria or alternatives.

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?

With no annotations, the description carries the full burden and does meaningful work: it discloses cost ($0.003 USDC/call), the payment protocol (x402), the chain (eip155:8453), and the important billing rule 'No match = not charged.' It doesn't state how ambiguous addresses are resolved (single best match vs. candidates), required wallet/auth preconditions for x402, or rate limits.

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 dense sentence with the cost/chain metadata bracketed up front and the capability plus edge-case billing rule following. No filler, nothing repeated, and the most decision-relevant info (price, US scope, no-charge on miss) is front-loaded.

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 correctly compensates by enumerating the returned fields and noting GEOIDs are official. For a one-parameter tool this is nearly complete; only multi-match/ambiguous-address behavior is left unspecified.

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% and the schema already gives a format example ('350 5th Ave, New York, NY 10118'). The description reinforces 'one US street address' but adds no additional syntax, normalization, or failure-mode guidance beyond 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?

Specific verb + resource ('Geocode one US street address'), names the data source (U.S. Census Bureau), and enumerates the exact outputs returned (lat/lon, tract, block group, ZCTA, GEOIDs). The 'US street address' scoping also implicitly separates it from uk_postcode in the sibling 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?

Clear context: single-address, US-only geocoding, so an agent knows not to route Canadian/UK lookups or batch lists here. It doesn't explicitly name uk_postcode as the alternative for non-US addresses, nor state what to do with ambiguous/multi-match addresses — the only gap.

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?

With no annotations, the description carries the burden and does well: it discloses the $0.001 USDC x402 payment on eip155:8453, the cryptographic verification steps performed, and the shape of the result. The one notable gap is failure behavior — it does not say whether an invalid signer produces an error, a false verdict, or a distinct status.

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 dense sentence with the cost/payment metadata front-loaded and the core purpose immediately after. Nothing is redundant, though the bracketed payment prefix competes slightly with the purpose statement for the agent's first attention.

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 tool with no output schema, the description covers cost, verification logic, and return fields (verdict, score, jobId, bytes32 reason), which is nearly everything an agent needs. Only the failure/error path is left unspecified.

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 already says 'attestation.token from evaluate_deliverable'. The description restates that origin without adding format, encoding, or provenance details, so the 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 — verifies an attestation token — and then spells out the mechanism (EIP-712 signer recovery, evaluator check) plus the returned fields. It is unmistakably distinct from siblings like verify_usdc_payment or x402_probe, since it names the issuing tool evaluate_deliverable as the token source.

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 phrase 'token from evaluate_deliverable' establishes the clear precondition and workflow position: call this after evaluation to confirm authenticity. There is no explicit when-not guidance or named alternative for related verification tasks, 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.

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

With no annotations the description carries the burden, and it discloses the paid-call pricing model ($0.002 USDC/call, x402, eip155:8453), the billing edge case (unknown tx = not charged), and the return shape ('verdict + decoded transfers'). It stops short of saying whether a failed verification returns a false verdict or an error, which is the one behavioral detail an agent still 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?

A single dense sentence plus a bracketed pricing banner; every clause earns its place and the check list is front-loaded. The price tag preceding the purpose is slightly awkward ordering but costs almost nothing.

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 6-parameter tool with no annotations and no output schema, the description covers purpose, checks, cost, billing edge case, and return contents. It lacks only detail on the verdict's shape and failure-mode behavior, which matters because there is no output schema to fall back on.

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 adds real semantics by mapping params to checks — 'at least min_amount', 'enough confirmations', and the parenthetical that 'from' is optional while 'to' is expected. That clarifies the optionality contract beyond the schema's per-field text.

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 ('Verify a USDC payment on Base') and enumerates exactly what is checked: tx success, recipient/sender match, min_amount, confirmations. This clearly separates it from siblings like usdc_balance (balance read) or x402_probe (endpoint probing).

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 (verify a payment before trusting it) and the billing rule 'Unknown tx = not charged' tells the agent it is safe to call speculatively, but there is no explicit when-to-use or when-not-to-use versus usdc_balance / x402_probe / sanctions_crypto_address.

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?

With no annotations, the description carries the full burden and does well: it discloses the cost ($0.01 USDC/call), the protocol and chain (x402, eip155:8453), that the probe request is unpaid (non-destructive), and the red-flag signal it returns. It does not cover failure modes or what happens when no 402 is returned.

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 dense sentence, front-loaded with cost and protocol tag, then purpose, then output fields. No 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?

There is no output schema, and the description effectively compensates by enumerating the decoded offer fields, so an agent knows what to expect back. For a two-parameter probe with no annotations, the only missing piece is error/edge-case 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 coverage is 100% and both parameters (url, method) are documented in-schema. The description implies the URL is a paid endpoint and that a single request is made, but adds no syntax or format detail beyond the schema, so the 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: 'Pre-payment check of an x402 endpoint' that makes 'one unpaid request' and decodes the 402 offer. The decoded field list (network, USDC or not, USD price, payTo, testnet, red flags) makes it clearly distinct from siblings like verify_usdc_payment and mcp_probe.

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?

'Pre-payment check' gives a clear usage context: run this before committing funds to an endpoint. It does not explicitly name alternatives or exclusions (e.g., when to follow up with verify_usdc_payment), 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.