Cited Brief

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

Annotations already declare readOnlyHint and openWorldHint, and the description goes beyond them with genuinely operational detail: pricing at $0.01 USDC per call via x402, no charge if the lookup services are down, and no AI in the loop. It does not cover latency, rate limits, or partial-failure behavior per id, so it is useful but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and tightly packed, though it is a long semicolon-chained sentence that mixes purpose, guidance, billing, and provenance claims. Every clause carries some information, but the density makes it slightly harder to scan than a split structure would 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?

There is no output schema, so the description carries the full burden and it does: it enumerates the returned fields (existence, title, authors, year, venue, citation count, retraction flag) plus cost and failure billing. An agent has everything needed to decide, call, and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented in the schema, including the same-order requirement for titles and accepted id formats. The description restates the 1-10 bound and the title-comparison behavior rather than adding format or edge-case detail beyond the schema; 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 ('Looks up 1-10 DOIs or arXiv ids') and enumerates exactly what is checked: existence, title, authors, year, venue, citation count, retraction status. It is clearly separable from siblings like check_links or check_quote without opening any 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?

Gives a concrete scenario ('Pass the titles you cited to see if they match the real ones. Catches made-up references'), which tells an agent when this tool is the right choice. It does not, however, name an alternative or state when to prefer a sibling such as check_quote for quoted text, so it stops short of full 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?

With readOnlyHint and openWorldHint already covering the safety profile, the description still adds substantial non-obvious behavior: it is deterministic ('No AI involved'), a dead link is a valid non-failure result, a request with no usable URL is not charged, and the call costs $0.01 USDC via x402. Billing and failure semantics are exactly the kind of context annotations cannot convey.

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?

Four tight sentences lead with the resource and outputs, then usage, then behavior and pricing. Nothing is padded, though the billing sentence is dense enough that it slightly blurs the front-loaded structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description takes on the burden of describing return values, and it does so explicitly (status, redirect endpoint, title, soft-404 warning). Combined with the cost and failure-handling rules, an agent has everything needed to call it correctly.

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% for the single 'urls' parameter, so the baseline is 3. The description goes slightly beyond the schema by restating the 1-10 cardinality and adding the charge rule tied to usability of the supplied URL, which clarifies what counts as a valid input.

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 names a specific verb and resource ('Checks 1-10 URLs') and enumerates exactly what is returned: HTTP status, redirect destination, page title, and a soft-404 warning. That enumeration distinguishes it from siblings like check_doi, page_text, and robots_check without the agent needing to open another 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?

'Use it to catch dead or made-up citations' gives a clear use context, and the citation framing separates it from the DOI/quote checkers. However, it never states when NOT to use it or names a sibling alternative for a related task (e.g. check_doi for DOIs), so it stops 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?

Beyond readOnlyHint/openWorldHint it discloses the matching algorithm (case, spacing, quote and dash styles ignored), that matching is deterministic ("No AI involved"), the failure billing policy ("if the page can't be read you are not charged"), and the exact cost mechanism ($0.01 USDC per call via x402). That is unusually rich operational context for an agent deciding whether to spend 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?

Three short sentences, front-loaded with the core behavior, then the use case, then cost/failure semantics. No filler and nothing repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description partially compensates by stating the return ("the surrounding text"). It does not describe the response shape per quote or how misses are represented, which is the main remaining gap for an agent parsing results.

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 url and quotes are already documented; baseline would be 3. The description adds meaning beyond the schema by stating the 1-10 count limit and the normalization rules, which tell the agent it need not reproduce exact punctuation or spacing when building the quotes array.

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 precise verb+resource: verifying that 1-10 quotes literally appear on a given URL, plus the normalization rules applied and the returned surrounding text. The scope is distinct from siblings like check_doi (citation identity) and page_text (raw extraction), 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?

"Use it to catch made-up citations" gives a concrete when-to-use context, and the 1-10 quote bound implies batching. There is no explicit when-not or pointer to an alternative (e.g., check_doi for DOI resolution), so it stops short of full 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?

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the pricing model ($0.10 USDC via x402), the verification behavior (verbatim quotes re-checked on the live page), the failure handling (claims that fail are dropped), and the no-charge-on-total-failure guarantee. These are material facts an agent cannot get from 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?

Two sentences, front-loaded with the core action and followed by the differentiators (verification, billing). No filler or repetition; every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does convey the return semantics (claims each backed by a verbatim quote) and the cost model, which is enough to call it correctly. It stops short of describing the response shape or what happens with partial successes, a minor gap for a tool whose value hinges on its cited output.

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 two parameters are already fully documented in the schema (maxItems 5, maxLength 500). The description restates the 1-5 page bound but adds no format or syntax detail beyond what the schema provides, 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 and resource ('Answers a question from 1-5 web pages you name') with an explicit scope bound. This is clearly distinguishable from siblings like check_quote (verifies a single quote) and page_text (returns raw text), since this one produces a grounded answer.

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: bring a question and 1-5 URLs when you want a cited answer. However, the description never names alternatives or states when NOT to use it (e.g., use check_quote to validate an existing quote, page_text to just read a page), so the agent must infer the routing.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses the pricing model ($0.02 USDC per call via x402), the no-charge failure condition, deterministic behavior ('No AI involved'), and TLD coverage breadth. These are material facts an agent needs before invoking a paid, open-world 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?

A single dense paragraph that front-loads the returned data before moving to usage, coverage limits, and price. Every clause carries information, though the enumeration of TLDs and flags is slightly sprawling.

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 covers return contents, trust-judgment purpose, supported/unsupported TLDs, pricing, and billing exemptions — everything an agent needs to decide and call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter with 100% schema description coverage, so the schema already documents that it accepts a domain name or URL with an example. The description adds only TLD applicability context, not new meaning about the parameter itself; 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 (domain age/registration lookup plus live DNS) and enumerates the exact data returned: created, expires, registrar, status, nameservers, SPF, DMARC. It is unmistakably distinct from siblings like check_doi, check_links, robots_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?

Gives a clear use case ('judge how trustworthy a site is') and documents applicability limits (works for most TLDs; no charge when the registry has no public lookup such as .de, .jp, .co). It does not explicitly name a sibling alternative, but the siblings cover entirely different resources, so no routing ambiguity remains.

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?

On top of readOnlyHint/openWorldHint, it discloses real behavioral traits: markup stripping, a 100,000-character truncation ceiling, and notably a billing model ($0.01 USDC per call via x402) plus a no-charge-on-failure guarantee. That pricing and failure behavior is material for an agent deciding whether to invoke, and is not in the annotations. Remaining gaps (rate limits, timeouts, auth) keep it from 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?

Three short sentences, front-loaded with what the tool returns before the cost/failure caveats. Every sentence carries distinct information (output shape, truncation, billing) with no 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 no output schema, the description does the work of describing the return value (title plus readable text) and its truncation limit, and it covers cost and failure handling. What is missing is operational context an agent might want, such as timeout, redirect, or JS-rendered-page 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 description coverage is 100%, so both parameters (url, max_chars) are already documented with defaults and bounds. The description adds only the 100,000-character cap, which merely restates the schema maximum, 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?

The description states a specific verb and resource ("Fetches a public web page and returns its title and readable text") and adds the scope of the output (no scripts, styles or markup). It is clearly distinguishable in kind from the sibling check_* tools, though it never names one as an alternative or 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?

Usage is only implied: an agent can infer this is the tool to call when it needs the readable text of a public page. There is no explicit when-to-use, when-not-to-use, or named alternative among the siblings (e.g. robots_check or check_links), so guidance remains at the minimum viable level.

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

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

Annotations already cover read-only and open-world nature, but the description adds genuinely useful behavioral facts: no AI is involved, the call is free if robots.txt cannot be read, and the price is $0.01 USDC via x402. That pricing/billing-exception detail is exactly the kind of context annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then behavioral and cost details in tight clauses. Slightly dense with parentheticals, but essentially every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly names what comes back (matching rule, crawl-delay, sitemaps) as well as cost and the unreadable-robots.txt fallback. Complete enough to call correctly, missing only explicit alternative-tool routing.

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 parameters (url, user_agent) are fully documented there, including the default 'any crawler'. The description mentions matching rule, crawl-delay and sitemaps, which are return values rather than parameter guidance, so it adds no parameter meaning beyond the schema. Baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource: reads the site's robots.txt and reports whether a crawler may fetch a URL. The RFC 9309 rule semantics (longest match wins, Allow wins ties) make it unambiguous versus siblings like domain_check or check_links.

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 description (checking crawl permission for a URL), but it never says when to prefer this over sibling tools such as domain_check or check_links, nor any preconditions beyond the input URL being public http(s). Adequate but no explicit routing guidance.

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