WebExtract

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses real operational behavior: robots.txt is honored, the free tier is capped at 50 calls/day per IP, and prepaid credits require an 'Authorization: Bearer <key>' header. These are exactly the constraints an agent needs to avoid surprise failures. It stops short of covering failure modes such as blocked pages or non-HTML content.

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 no filler, front-loading what the tool does before the operational constraints. The second sentence packs quota and auth details densely but every clause is actionable.

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 structure need not be explained, and the description nonetheless summarizes it. Auth, quota, and scope are all covered. The one missing piece for this tool's complexity is disambiguation from page_markdown, which is 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?

There is a single parameter with 100% schema description coverage ('Public http(s) URL'), so the schema already carries the semantics. The description only echoes the public-URL constraint, adding nothing material beyond what the schema states; 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 concrete verb and resource — fetch a public web page and return Markdown plus fixed-schema JSON — and even enumerates the JSON payload categories (article metadata, product/price, tables). It is clear, but it never distinguishes itself from the sibling page_markdown, leaving the agent to guess which extractor 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?

Usage is only implied: 'public web page' and 'robots.txt respected' signal the accepted scope, and the auth/credit sentence hints at paid traffic. There is no explicit when-to-use, no when-not-to-use, and no routing to page_markdown, so the agent must infer the boundary between the two 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 only cover readOnly and openWorld; the description goes well beyond them by disclosing robots.txt compliance, the free-tier rate limit (50 calls/day per IP), and how to authenticate with a Bearer key for prepaid credits. These are exactly the operational constraints an agent needs 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 tight sentences: capability and output first, then cost/alternative, then rate limits and auth. No filler, and the most decision-relevant facts are front-loaded.

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 an output schema present, return-format explanation is unnecessary, and the description covers the remaining gaps: cost, sibling alternative, rate limits, auth, and robots.txt behavior. Nothing material is missing for correct 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 coverage is 100% for the single url parameter, so the schema already documents it. The description adds the Authorization header convention, which is not represented in the input schema and would otherwise be invisible to the caller.

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 (fetch) and resource (public web page), and specifies the output format (clean Markdown only). It also distinguishes itself from the sibling extract_url by naming it and noting the cost difference.

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?

Explicitly positions itself against extract_url on cost ('Cheaper than extract_url (0.4 credit)'), giving the agent a selection rationale. It stops short of stating when extract_url would be the better choice (e.g., richer extraction), so exclusions are 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.