AgentRead

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses important behavior: JavaScript is not executed, navigation/ads/cookie banners/scripts are removed, the call is paid via x402 at $0.003 per successful call, and output may be truncated. It also lists the return envelope and extraction metadata, giving the agent strong operational context.

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 purpose is front-loaded and the description is dense with useful information, not filler. The final return-field list is long, but because there is no output schema it earns its place; the description could be slightly more structured for readability.

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 description is largely complete for a no-output-schema tool: it explains the extraction behavior, payment model, JavaScript limitation, truncation, and the shape of the returned JSON. It still leaves sibling-tool routing and error/failed-call behavior implicit, which keeps it short of fully complete.

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

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

Schema description coverage is 100%, and the schema already explains url constraints, includeLinks, and maxCharacters in detail. The description does not add meaningful parameter-level semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the specific action and resource: fetch a public web page and return its main content as clean Markdown. It also names the extracted artifacts (title, description, headings, metadata), so the tool’s purpose is unambiguous. It does not, however, distinguish this tool from sibling extract_url_structured or inspect_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?

Usage is implied by 'Fetch a public web page' and the note that it does not execute JavaScript, which helps an agent understand suitable pages. The description does not explicitly say when to use this versus extract_url_structured or inspect_url, nor does it state exclusions beyond public/no-JS pages.

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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely non-obvious behavior: deterministic HTML processing with no LLM involvement, and an x402 payment of $0.005 per successful call. That cost/auth disclosure is exactly the kind of context annotations cannot express. It stops short of covering failure modes or what happens on an unpaid/failed 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?

Front-loaded with purpose, then cost, then return shape — a sensible priority order with no filler sentences. The trailing field-by-field JSON enumeration is dense and near-schema-like, but since there is no output schema it earns most of its space.

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 naming every returned field including the truncation flags, which an agent needs to detect partial results. Cost model and determinism are also covered. The remaining gap is sibling differentiation and error/payment-failure behavior, which matters for a tool with both network access and a per-call charge.

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 three parameters including defaults, bounds, and URL constraints are already documented structurally. The description lists output components rather than parameter meaning, adding nothing about `includeLinks`, `maxCharacters`, or `url` beyond the schema. 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 ("Fetch a public web page and return structured data") and enumerates the exact outputs (metadata, markdown, headings, links), which is far more precise than a name restatement. It does not, however, distinguish itself from the sibling `extract_url` or explain what makes this the "structured" variant, so an agent comparing the two must open their schemas.

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 when-to-use / when-not-to-use guidance and no mention of the `extract_url` or `inspect_url` siblings, despite a name that strongly implies overlap. Only implicit signals exist ("public web page", "structured data"), leaving the agent to infer routing between three similar tools.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: it discloses a bounded cost profile by downloading only 'a small prefix of the page' rather than the full document. It doesn't state rate limits or failure semantics, which keeps it short of a 5.

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

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

One compact sentence plus a short cost caveat, with the most important information (what is checked) front-loaded. The long enumeration of outputs is dense but each item is actionable for deciding whether to call it.

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?

An output schema exists, so return-value explanation is unnecessary and the description correctly avoids it. For a read-only single-param probe, the remaining gap is sibling routing: it doesn't say when to prefer extract_url or extract_url_structured over this inspection step.

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?

Only one parameter with 100% schema coverage, so the schema already documents the URL constraints (absolute, public, default ports, no credentials, no IP literals). The description reinforces 'public URL' but adds no syntax or format detail beyond the schema, which is the baseline-4 case for a single fully documented param.

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?

Uses a specific verb ('check') and enumerates the concrete outputs: reachability, HTTP status, final URL after redirects, content type, page title, and extraction viability. It hints at the boundary with the extraction siblings ('whether extraction is likely to work') but never names them, so differentiation is implied rather than stated.

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 word 'free' and the extraction-likelihood output strongly imply this is a cheap pre-flight step before extract_url, but there is no explicit when-to-use instruction, no exclusion, and no named alternative. The agent must infer the routing from the 'free, lightweight' framing.

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