Exepal

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

The description adds genuinely non-obvious behavioral context beyond annotations: pricing ($0.25 USDC per call, Base, x402) and the failure not being charged. That's real value not in readOnlyHint/openWorldHint. It doesn't explain what a 'score' returns, but the payment terms are well disclosed.

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 tight sentences, zero waste, with the core action front-loaded and payment terms compactly appended. Every clause carries information.

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

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

For a scoring tool with no output schema, the description never says what the result looks like (a numeric score, sub-scores, rationale). Pricing and failure behavior are covered, but the return shape is a notable gap an agent would want.

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?

One parameter with 100% schema description coverage, including nested field docs for cta/hook/script/platform. The description adds nothing about the creative object beyond the schema, 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 ('Score one ad creative'), and the word 'one' implicitly contrasts with the batch sibling. It stops short of explicitly naming or differentiating against ad_creative_score_batch, but an agent can identify the operation.

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 'one ad creative' phrasing weakly implies the single-item case vs the batch sibling, but there is no explicit when-to-use guidance, no prerequisites, and no named alternative. Usage must be inferred from the quantity wording.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful non-annotation context: the exact price, the payment rail (x402 on Base, USDC), and crucially that failed calls aren't charged, which affects the agent's retry calculus.

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 operation, then billing terms. No filler and every clause carries information the 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?

There is no output schema and no description of what a 'score' returns (numeric score, per-dimension breakdown, rationale), so the agent cannot anticipate the result shape. Billing and failure semantics are complete, but the return contract is a notable gap.

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 reported at 0% at the top level and the single parameter is a nested array of creative objects; the description says nothing about what constitutes a valid creative (script, hook, cta, platform). It only restates the maxItems of 10, which the schema already enforces.

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: 'Score up to 10 ad creatives', naming the operation and the batch limit. It doesn't explicitly distinguish itself from the sibling ad_creative_score (single-item), leaving the agent to infer the batch/single split from the name and 'up to 10'.

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?

'Up to 10 ad creatives' implies this is the bulk variant, but there is no explicit instruction on when to use this versus ad_creative_score, nor any guidance on cost trade-offs beyond the raw price. Usage is implied 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?

Annotations already cover read-only and open-world behavior, so the description's real contribution is the cost model: $3.00 USDC on Base via x402, with no charge on failure. That is exactly the kind of context an agent needs before invoking a paid tool, though latency and rate-limit behavior remain undisclosed.

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 sentences with no filler: purpose and scope first, cost model second. Nothing repeats the name or title unnecessarily and 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 should say something about what the report contains — visibility scores, per-engine breakdown, competitor comparison — but it does not. Payment behavior is well covered and annotations carry the safety profile, yet the return shape and tier relationship remain gaps.

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 every parameter is already documented, and this sets the baseline at 3. The description adds only that 20 prompts and 'all engines' are the defaults, without explicitly tying those to promptCount or engines, so it adds marginal value over 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 output ('AI brand visibility report') with concrete scope (20 prompts, all engines), which tells an agent what it gets. It sits between ai_visibility_quick and ai_visibility_deep but never names either sibling, so differentiation is only implicit via the '20 prompts' detail.

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 guidance on when to choose this over ai_visibility_quick or ai_visibility_deep, which are the obvious alternatives in the sibling list. The only decision-relevant fact given is price, which is insufficient to route between tiers.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds important behavioral context: it is a paid call, costs $7.00 USDC on Base via x402, and is not charged if the call fails. That payment and failure-charge behavior is valuable beyond the annotations.

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

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

The description is compact and front-loaded: report scope first, then pricing and payment behavior. Every clause adds useful information with 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?

It covers the tool's purpose, scope, payment model, and failure-charge policy, which is important for a paid call. However, with no output schema and no description of what the report contains, an agent still lacks a clear picture of the returned artifact and why this deep tier should be chosen over 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 description coverage is 100%, so the schema already documents all seven parameters well. The description adds only that this tier uses 50 prompts and all engines, which lightly clarifies the default scope but does not explain optional filters or how promptCount is capped by tier.

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 identifies a specific report resource and scope: AI brand visibility, deep report, 50 prompts, all engines. This distinguishes it reasonably well from ai_visibility_quick implicitly, though it does not explicitly name the sibling 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?

It does not state when to use this tool versus ai_visibility, ai_visibility_quick, or serp_ai_monitor_deep. The word 'deep' and '50 prompts, all engines' imply a comprehensive use case, but there is no explicit routing guidance or exclusion criteria.

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

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

Annotations already declare readOnlyHint and openWorldHint. The description adds valuable context beyond that: exact price ($0.50 USDC), payment mechanism (x402 on Base), and failure policy ('not charged if the call fails'). It also confirms the tier limits (5 prompts, 1 engine).

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 compact sentence with two clauses, front-loaded with purpose and followed by cost/payment details. Every clause carries essential information; 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?

The definition covers purpose, cost, payment, failure policy, and tier limits, and the rich schema describes all 7 parameters. It lacks any description of the return value, but with no output schema and annotations covering read-only/open-world behavior, this is a minor gap for selection purposes.

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 meaning by specifying the quick tier's caps: 5 prompts and 1 engine, which clarifies the promptCount and engines parameters beyond the schema's generic 'capped by the tier' and 'subset of engines'.

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 (AI brand visibility) and scope (quick check, 5 prompts, 1 engine). It implicitly distinguishes from the deeper sibling tools via 'quick check', though it does not name them 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 phrase 'quick check' implies a use case for fast, low-cost sampling, but there is no explicit guidance on when to choose this over ai_visibility or ai_visibility_deep, nor any when-not conditions.

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

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely useful context beyond them: cost ($0.10 USDC per call on Base), the x402 payment mechanism, and the no-charge-on-failure guarantee. It does not describe latency or what data is returned, which keeps 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?

Two tightly written sentences with zero waste: capability first, then the billing constraint that materially affects invocation decisions. Nothing is buried or redundant.

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

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

Payment terms and safety profile are well covered, but with no output schema the description should say what 'enrichment' actually returns (firmographics, tech stack, employee count, etc.). For a paid tool whose value depends on returned data, that gap matters.

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 parameter with 100% schema description coverage ('Company domain, e.g. stripe.com'), so the schema already carries the semantic load. The description adds nothing about domain format, normalization, or subdomain handling, 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 action and resource: 'Company enrichment for one domain,' which tells an agent exactly what operation and scope to expect. The 'one domain' phrasing implicitly distinguishes it from the batch sibling, though it never names company_enrich_batch directly.

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 by the scope phrase 'for one domain,' which suggests the batch tool handles multiple domains, but neither the alternative nor any exclusions or prerequisites are stated. An agent must infer when to pick this over company_enrich_batch.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful non-schema context: cost ($0.80 USDC per call on Base), the x402 payment mechanism, and the no-charge-on-failure guarantee, which an agent needs before invoking a paid 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 tight sentences, zero filler, with the capability stated first and the billing terms second. Nothing is wasted or buried.

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 burden of indicating what enrichment data comes back, and it says nothing about returned fields, structure, or per-domain error behavior. Billing and scope are complete, but the return-value side is left blank for a read tool.

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

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

With one parameter at 100% schema coverage (including maxItems: 10), the schema does the documentation work. The description's 'up to 10 domains' merely restates the schema bound and adds no format hints (e.g., whether bare domains or URLs are expected).

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 ('Company enrichment for up to 10 domains'), which is clear and actionable. It implicitly separates itself from the single-domain sibling company_enrich via the batch framing, but never names that alternative 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 'up to 10 domains' cap implies this is the multi-domain path, so usage is reasonably deducible. However, it gives no explicit guidance on when to choose this over company_enrich or the batch scoring siblings, and no prerequisites or exclusions.

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?

Adds real information beyond the readOnlyHint/openWorldHint annotations: a concrete price ($0.20 USDC per call on Base via x402) and the failure-billing policy (not charged if the call fails), plus the conditional outbound fetch. It does not disclose latency, rate limits, or what the returned score looks like, but the payment semantics are the highest-value missing piece and 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?

Two sentences, zero padding: what it returns first, then cost and billing policy. The payment caveat is a sentence fragment that still carries essential decision information, and nothing is 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?

Covers the two things an agent most needs to decide and act: the paid-call cost model and the optional fast path. For a read-only scoring tool with no output schema, the main remaining gap is what the score means (range, components, confidence), which would help interpretation but not invocation.

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 handle, platform enum, and the optional profile object are all already documented. The description repeats the fetch-skipping behavior of `profile` without adding format, size, or required-fields detail for that nested object, 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 concrete output (a vetting score) for a concrete resource (one creator profile), which separates it from siblings like ad_creative_score (ads), ai_visibility (AI search), and company_enrich (companies). The verb is implicit in "vetting score" rather than a stated action, but the resource and scope are unambiguous.

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: "for one profile" signals a single-creator operation, and "fetches the profile if stats not supplied" hints at the optional-profile path. There is no explicit when-to-use statement, no conditions favoring siblings, and no note on when a batch or alternate tool would be preferable.

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 access, and the description adds genuinely non-obvious context: cost of $0.005 USDC per call on Base via x402 and, critically, that failed calls are not charged. It stops short of disclosing latency, rate limits, or whether the returned grade is cached.

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, zero filler: the capability list comes first and the pricing/charging policy second. 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 compensates by enumerating the returned fields, and the payment model is disclosed. What is missing is any hint about response shape, size, or how partial failures (e.g. no RDAP for a ccTLD) surface in 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 coverage is 100% and each parameter already carries a detailed description (including the ccTLD/RDAP caveat and the URL/email reduction rule). The description adds no parameter guidance beyond the word 'domain', 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?

Names the resource (domain) and enumerates exactly what is returned: DNS, MX, SPF/DMARC/DKIM grade, RDAP registrar/dates, hosting, tech stack, risk flags. No sibling tool (ad_creative_score, company_enrich, ai_visibility, serp_ai_monitor, read) overlaps, so the agent can route unambiguously.

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 enumerated data types — an agent infers this is the tool for domain-level inspection. But there is no explicit when-to-use framing, no statement of when not to use it, and no alternative named (the closest siblings, company_enrich and ai_visibility, are never referenced).

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 only declare readOnlyHint and openWorldHint; the description adds genuinely new behavior: a fixed price of $0.005 USDC per call on Base via x402 and the refund rule that failed calls are not charged. That is exactly the kind of cost/auth context annotations cannot express, though rate limits and failure modes other than billing are unstated.

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: the first defines what is returned, the second defines cost and billing behavior. Front-loaded, zero filler, nothing repeated from structured fields.

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 usefully enumerates the returned fields, and it covers the payment model for a metered tool. The main residual gap is that behavioral limits (no JS rendering, public http(s) only) are documented only in the schema rather than surfaced in the description.

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

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

Schema description coverage is 100%, so all five parameters (url, links, format, images, maxChars) are already fully documented with defaults and enums. The description only echoes format ('markdown or text') and links at a high level, adding no syntax or constraint detail 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 specific verb (read) and resource (one page URL) and names the output payload: clean markdown/text plus title, description, author, date and links. The phrase 'one URL' implicitly separates it from the sibling read_batch, 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?

Usage is only implied by 'one URL' – an agent can infer single-page reads vs. read_batch, but there is no explicit when-to-use statement, no exclusions, and no mention of the static-HTML/no-JavaScript constraint (which lives only in the schema).

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 safety, yet the description adds meaningful non-obvious behavior: a per-call price of $0.03 USDC on Base via x402 and the fact that failed calls are not charged. That is real cost/risk context an agent cannot get from annotations. It still omits what happens on per-URL failures within a batch or how results are 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?

Two sentences, both earning their place: the first defines the operation and batch bound, the second front-loads cost and the no-charge-on-failure guarantee. No filler or hedging.

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 5 parameters, 40% schema coverage, and no output schema, the definition should explain the undescribed options and the shape of results (one blob vs. per-URL results, ordering, partial failures). Instead it is silent on all of these, leaving the agent guessing how 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 description coverage is only 40%: only urls and maxChars carry descriptions. The description reinforces the 10-URL cap but says nothing about links, format (the one enum), or images, so three of five parameters remain undocumented in both schema and 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?

"Page reader for up to 10 URLs" gives a specific verb (read pages) and resource (URLs) plus the batch bound. It does not distinguish itself from the sibling tool "read", which is presumably the single-URL variant, so the agent must guess which to pick.

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 "up to 10 URLs" phrasing implies batch usage, so the use case is inferable, but there is no explicit statement of when to choose this over the sibling "read" tool, and no exclusions, prerequisites, or failure-mode guidance.

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

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds genuinely new behavioral facts: cost of $0.70 USDC per call, payment via x402 on Base, and no charge on failure. These are exactly the cost/auth details an agent needs before incurring a paid call; only the response shape is left unstated.

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 sentences with zero waste: the capability and its limits come first, pricing and failure-billing second. Nothing is repeated from the schema or annotations.

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?

Safety and cost are fully covered, but with no output schema the description gives no hint of what a response contains (SERP results, AI answer mentions, rank deltas via previousSnapshot). For a monitoring/comparison tool with a previousSnapshot input, that gap matters.

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 every parameter is already documented, establishing a baseline of 3. The description adds only the tier semantics ('up to 10 keywords') that clarify what 'capped by the tier' means for the keywords array, but says nothing about country/language/previousSnapshot usage.

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+resource: 'SERP + AI answer check' for keywords against an AI engine, with an explicit tier limit (10 keywords, 1 engine). This implicitly distinguishes it from serp_ai_monitor_deep and the ai_visibility family, but it never names or routes to 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?

No explicit statement of when to use this versus serp_ai_monitor_deep (presumably a deeper tier) or ai_visibility/ai_visibility_quick. The only selection signal is the implicit 'up to 10 keywords on 1 engine' cap, leaving the agent to infer the trade-off.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the description is not obligated to establish safety. It adds genuinely useful non-schema behavior: the $2.50 USDC price on Base, x402 payment, and that failed calls are not charged — a material fact an agent must weigh before invoking.

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, zero filler, with scope front-loaded before the cost/payment caveat. Every clause carries information an agent needs before calling.

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?

Cost and scope are covered, and params are fully specified in the schema, but with no output schema the description never says what comes back — rankings, AI answer mentions, competitor presence, or how previousSnapshot changes the response. For a paid, nested-object tool that is a real gap.

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 every parameter including brand, domain, country, language and previousSnapshot is already documented. The description only restates the keyword cap ('up to 25'), adding no format or constraint 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?

Names a specific verb and resource: a SERP plus AI-answer check across all AI engines, with a stated cap of 25 keywords. The 'deep'/25-keyword scale implicitly separates it from serp_ai_monitor and ai_visibility_quick, but it never names a sibling or states the axis of difference 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?

There is no guidance on when to pick this over serp_ai_monitor, ai_visibility, ai_visibility_deep or ai_visibility_quick. The keyword cap hints at 'use this for larger keyword sets' but no condition, prerequisite, or exclusion is stated.

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