ViewportWitness by Apex Labs

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

Annotations already signal readOnlyHint=false and destructiveHint=true, and the description adds valuable context beyond them: the exact cost, the payment mechanism, and the client requirement. It also describes output characteristics ('bounded performance evidence', 'plain-English diagnosis', 'safe structural locator hints'). No contradiction with annotations is present.

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

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

Three sentences, each earning its place: the first packs the core function and outputs, the second states cost, the third states the auth prerequisite. The most important information is front-loaded, and there is 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?

For a tool with no output schema, the description does a good job of explaining what the agent will receive: performance evidence, diagnosis, and locator hints. It also covers cost and payment prerequisites. It could be more complete by explaining what happens if the x402 payment is not authorized, but overall it is sufficiently complete for the tool's complexity.

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 0%, and the description does not mention the url parameter at all. The schema itself defines url with format and maxLength, but the description adds no semantic guidance about what URLs are acceptable or how they are used. With low coverage, the description should compensate, and it does not.

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 a specific action ('Run browser QA') and resource ('page') across three named viewports, with concrete outputs like performance evidence and diagnosis. It does not explicitly differentiate from sibling tools such as verify_page or compare_page, so it stops short of 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?

The description provides clear context on prerequisites: it costs $0.08 USDC via x402 and requires an x402-aware client, explicitly noting that standard AI assistants cannot automatically sign x402. This gives an agent important selection criteria, though it does not name alternatives or state when not to use the tool.

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 declare readOnlyHint=false, openWorldHint=true, and destructiveHint=true, which is unusual for a comparison tool. The description adds critical behavioral context: it costs $0.12 USDC via x402 and requires an x402-aware client, which is a significant operational constraint. However, the destructiveHint=true annotation is not explained in the description—it's unclear what destructive side effect occurs. This is a minor gap given the description does disclose the payment and client requirements.

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

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

Three sentences with no waste. The core function is front-loaded, outputs are listed compactly, and the cost/client constraint is saved for the end. Every sentence earns its place.

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 2-parameter tool with no output schema, the description covers the main inputs, outputs, cost, and client requirement. It doesn't explain the destructiveHint=true annotation or what 'bounded performance evidence' means, but the core information an agent needs to decide whether to call this tool is present. The missing output schema is a structural gap, not a description 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 description coverage is 0%, so the description must compensate. It mentions 'url' and 'baselineJobId' implicitly by saying 'Compare a page against a completed ViewportWitness baseline job'—the page maps to url and the baseline job maps to baselineJobId. However, it doesn't add detail about URL format, whether the URL must be publicly accessible, or how to obtain a baselineJobId. The description adds some meaning but doesn't fully compensate for the 0% schema 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 clearly states the tool's function: comparing a page against a completed ViewportWitness baseline job. It lists specific outputs (pixel-diff percentages, accessibility issue IDs, error deltas, performance evidence, diagnosis) and distinguishes it from siblings by naming the baseline job requirement. The verb 'compare' plus the resource 'page against baseline job' is specific and 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?

The description implies when to use this tool: when you have a completed baseline job and want to compare a page against it. It doesn't explicitly state when not to use it or name alternatives (check_page, get_report, verify_page), but the baseline job requirement provides clear context. The cost and x402 client requirement are important usage constraints that are disclosed.

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 destructiveHint=false. The description adds significant behavioral context: it is 'free', requires 'no payment', and specifies the polling pattern with exact statuses (complete, failed, retryable). This goes well 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?

Four short, purposeful sentences. The main purpose is front-loaded, and each sentence adds distinct value (purpose, cost, polling behavior, payment). No wasted words.

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, read-only tool with no output schema, the description covers the essential usage: what it retrieves, how to poll, and the terminal statuses. It does not specify the exact response structure, but for a polling tool this is adequate.

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 0% and the description does not explicitly describe the jobId parameter. However, the phrase 'previously submitted job' implicitly indicates the jobId identifies that job. It adds minimal meaning but does not fully compensate for the lack of schema 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?

The description clearly states the verb 'Retrieve' and the resource 'status or completed QA report' for a 'previously submitted job'. It is distinct from sibling tools like check_page, compare_page, verify_page which focus on pages, not reports.

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?

Provides clear context for when to use: polling a previously submitted job. Includes explicit polling instructions with target statuses. Does not mention alternatives, but siblings are unrelated, so no exclusion is necessary.

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 signal that this is not read-only, open-world, and potentially destructive, and the description does not contradict them. It adds valuable behavioral context beyond annotations: the $0.10 USDC cost, the x402 client requirement, the three-viewport behavior, and the bounded performance evidence. It does not fully detail the nature of any destructive side effects, but the annotation covers that signal.

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: the core behavior comes first, followed by the assertion-type enumeration, then cost and client requirements. Every sentence contributes essential information, and there is no filler or repetition of 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?

For a paid, externally-facing verification tool with no output schema, the description covers the critical operational context: maximum assertions, assertion types, viewports, cost, and the x402 authentication requirement. The return value is only summarized as 'bounded performance evidence plus plain-English diagnosis,' leaving the exact response shape unstated. Still, this is adequate for an agent to judge whether and how to invoke the 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?

Schema description coverage is 0%, so the description must compensate, and it does: it lists all six supported assertion type names and the 'up to 20' limit, which maps directly to the assertions array's maxItems. It does not explain the 'value' and 'selector' subfields, but the schema's self-describing property names and required fields make those reasonably inferable. The 'url' parameter is unambiguous from its name and format.

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

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

The description clearly states the tool's function: checking up to 20 declarative assertions across three viewports and returning performance evidence plus diagnosis. It also lists the exact assertion types. However, it does not explicitly distinguish verify_page from its siblings like check_page or compare_page, so it misses the sibling-differentiation component of 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?

The description implies when to use the tool: when declarative assertion checks are needed across viewports. It also gives a critical constraint: an x402-aware client is required and standard AI assistants cannot automatically sign x402. But it never mentions alternatives or when to choose check_page, compare_page, or get_report instead, so usage guidance is only implicit.

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