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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context that annotations cannot express: a metered cost of 1 credit per call, and the shape of the returned insight set. It stops short of noting latency, rate limits, or that caching defaults to off.

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 that lead with the core action and output list, then the cost. The opening 'Analyze (AI).' merely restates the title and is the only wasted fragment.

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 compensates by enumerating the returned insight fields, and the credit cost is disclosed. For a single-required-parameter read/analysis tool with full schema coverage, this is close to complete; only sibling differentiation and cost-bearing edge cases are absent.

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 including cache, proxy, fields, custom_prompt, and custom_response is already documented in the schema. The description adds no parameter-level meaning beyond that baseline, which is appropriate but not additive.

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 ('analyzes any webpage') and enumerates the concrete outputs (insights summary, value proposition, features, categories, use cases, contact signals), so an agent knows exactly what it gets back. It does not, however, differentiate itself from siblings like 'content' or 'website_crawler', which also operate on webpages.

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: 'analyzes any webpage' suggests it is for AI-derived insight extraction, and the credit-cost note hints it is a paid call to use deliberately. There is no explicit when-to-use, when-not-to-use, or routing to the sibling tools that also take URLs.

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, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description usefully adds the cost model ('1 credit per call') and the managed-browser convenience, but says nothing about what is actually returned (inline image vs. hosted URL), latency, or failure behavior on unreachable pages.

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 with the core capability front-loaded and the cost note at the end where it belongs. The leading 'Capture (Screenshot).' duplicates the title, which is minor waste, but nothing else is padded.

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 30-parameter tool with no output schema, the description is thin: it never states whether the response contains image bytes, a URL, or an S3 link, which is the single most important omission for a capture API. The rich schema compensates for parameter knowledge but not for return-value expectations.

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% across all 30 parameters, so the schema does the heavy lifting and the baseline of 3 applies. The description adds no parameter-level meaning of its own and merely restates the supported output formats already enumerated in the format field.

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 ('captures webpages as PNG/JPEG/WebP or PDF') and lists concrete output formats, so the tool's function is unambiguous. It does not, however, distinguish this tool from siblings like content, analyze, or website_crawler, which arguably also touch a URL.

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 cases are listed (previews, QA, reporting, monitoring, archiving) and 'no headless setup' hints at why to choose this over rolling your own. But there is no explicit when-not guidance and no reference to the sibling tools or when website_crawler/analyze would be the better pick.

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, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful non-schema context — a fixed cost of 1 credit per call — but says nothing about response shape, caching behavior, or failure modes for what is a 17-parameter scraping request.

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 tight sentences, front-loaded with the core capability and ending with the cost caveat. The leading one-word 'Content.' merely restates the title and could be dropped, but otherwise there is no wasted wording.

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 17-parameter extraction tool with no output schema, the description does at least inventory the kinds of data returned (metadata, links, HTML/Markdown). It still leaves an agent guessing about the response envelope and how the many optional toggles combine, which matters given the absence of an output schema.

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

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

Schema coverage is 100%, so every parameter is already documented with examples, defaults, and allowed values in the schema itself. The description only loosely gestures at the HTML/Markdown toggles and adds no format or interaction detail 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?

The description names a specific verb (extracts) and enumerates concrete outputs — structured webpage data, metadata, links, HTML/Markdown — plus the scenarios it serves (SEO, monitoring, indexing, automation). It is clear on its own but never distinguishes itself from siblings like 'capture' or 'analyze', which an agent could easily confuse it with given the generic name 'content'.

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 listed use cases (SEO, monitoring, indexing, automation) imply when the tool is appropriate, which is better than nothing. However, there is no explicit guidance on when to choose this over 'capture', 'analyze', or 'website_crawler', and no stated exclusions or prerequisites.

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 the safety profile (readOnly=true, destructive=false, openWorld=true), and the description adds meaningful operational traits: a fixed one-hour lookback, no tenant scoping, and an activation gate where HTTP 403 means the caller must contact support. Return shape is not described, but with no output schema that is the main remaining 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?

Three short sentences, front-loaded with the resource and scope, then the scoping caveat, then the activation error. The leading "Stats." merely repeats the title and is the one wasted token.

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 two-optional-parameter read-only tool with no output schema, the description covers scope, time window, and the one likely failure mode (403/activation). It could say more about what the health payload contains, but nothing critical to calling it correctly is missing.

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

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

Schema coverage is 100%, so both parameters and their relationship ("Provide at least engine or path") are already documented. The description adds only the time-window framing, not additional syntax or semantics for path/engine, 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?

"Infrastructure health for an engine or endpoint over the last hour" gives a concrete resource (infra health) and scope (per engine/endpoint, one-hour window). The added note that it is "Not scoped to your account or tenant" implicitly separates it from account-oriented siblings like usage, though no sibling is named.

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 supplies context (one-hour window, tenant-agnostic, per-account activation) that implies when to reach for it, but never states when to use a sibling such as usage instead, nor any explicit exclusions beyond the 403 case.

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, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds the useful facts that the data is real-time and that it includes credit balance, but says nothing about freshness latency, caching, or failure modes when the account is unreachable.

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 the resource named up front and no padding. The leading 'Usage.' merely restates the title and tool name, which is a small waste, but the remainder 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 zero-parameter, no-output-schema tool, the description should convey what comes back, and it does at a high level (statistics plus credit balance). What it lacks is any resolution of the overlap with the 'stats' sibling and any hint of the response shape, which matters because there is no output schema.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate and the schema is trivially complete. Baseline 4 applies; the description correctly avoids inventing parameter talk.

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: 'Retrieve real-time usage statistics and credit balance for your CaptureKit account.' An agent knows this returns account consumption data. However, it does not distinguish itself from the sibling 'stats', which plausibly covers the same ground, so differentiation is missing.

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 when-to-use or when-not-to-use guidance is given, and no alternative is named. With a sibling called 'stats' in the same toolset, the absence of routing guidance leaves a real selection ambiguity unresolved.

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 readOnly, openWorld, and non-destructive, so the safety profile is covered. The description adds two meaningful facts beyond that: the request-mode/no-rendering behavior (so dynamically rendered content will not be fetched) and the cost of 1 credit per call. It does not describe pagination, rate limits, or error behavior on unreachable URLs.

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 operation, then modes, then cost. The only inefficiency is the redundant opening 'Website Crawler. Website Crawler API...' which restates the title twice before saying anything new.

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 four-parameter read-only fetch tool with full schema coverage and no output schema, the description covers operation mode, typical uses, and cost. The main gap is the default response shape, since it is unclear what comes back when 'return_page_source' is false, but that is partly addressed by the schema.

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

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

Schema description coverage is 100%, so all four parameters including 'query', 'fields', 'allow_redirects', and 'return_page_source' are already documented in the schema. The description adds no extra parameter detail such as URL format constraints or how 'fields' interacts with the HTML-source mode. Baseline 3 applies when the schema carries the semantics.

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

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

The description states a specific verb and resource: it fetches raw HTML from any webpage in request mode. The parenthetical '(no rendering)' and the listed use cases (scraping, audits, monitoring, link/metadata extraction) make the operation concrete. It does not name any sibling tool that would do a rendering-based capture instead, so differentiation is only implied.

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 cases are listed (fast scraping, audits, monitoring, link/metadata extraction) and 'no rendering' hints that JavaScript-heavy pages need a different tool. However, it never names an alternative sibling such as capture or content, nor does it state when this tool is the wrong choice. The guidance 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.