Tollkit Extract

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

With no annotations, the description fully carries the behavioral disclosure burden. It covers billing semantics (flat fee charged even on partial success, not charged when all URLs fail), duplicate removal, per-URL ok/error isolation, return ordering, and non-ranking behavior. This goes far beyond what the schema or title provides.

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 long but structured into scannable, labeled paragraphs, with the core usage rule front-loaded. Every section adds decision-relevant information; it is not padded, though it could be tightened slightly by reducing repeated comparisons to get_product_details.

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?

Given the output schema already exists, the description does not need to restate return fields. It covers when to use, cost, billing edge cases, duplicates, failure isolation, and the relationship to the sibling tool. An agent has everything needed to decide correctly and 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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by clarifying that URLs are processed in the given order, that duplicates are not billed twice, that payment is omitted on first call, and that allow_redirect applies uniformly to every URL. This lifts it above the baseline.

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 and resource: price the same product at multiple stores, up to 5 URLs in one call and payment. It explicitly differentiates from get_product_details by noting it returns one entry per URL so the caller can compare, without ranking or picking a winner.

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 guidance is explicit and actionable: 'USE THIS WHENEVER YOU HAVE MORE THAN ONE URL,' with concrete scenarios like comparing across stores and refreshing tracked prices. It also names the alternative, get_product_details, and gives a specific condition where that tool is the cheaper bet.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure, and it handles this thoroughly. It explains the headless-browser rendering, the x402 payment flow, cost, no-charge on failed extraction, redirect refusal behavior, 300-second caching semantics, and the guarantee that images are never invented.

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 long but well-structured, with clear section labels (USE THIS WHEN, DO NOT USE THIS FOR, RETURNS, HOW, COST) that make scanning easy. Every sentence provides actionable information needed for correct invocation, and the most important scoping guidance is 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?

The description is complete for a complex, paid, network-dependent tool: it covers when to use it, when not to use it, return-value semantics, payment mechanics, redirects, caching, and a free trial path. The output schema covers the exact return shape, so the description does not need to repeat it in full.

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?

Although schema coverage is 100%, the description adds significant operational meaning beyond the schema: URL constraints with concrete page examples, the exact first-call-without-payment flow including EIP-3009 signing and base64 encoding, and redirect behavior with a concrete discontinued-item scenario.

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 opening sentence states a specific action ('find out what a product is and what it costs') and an explicit resource ('from its page URL'). The description then scopes the tool to a single product page, explicitly excluding search/category pages and non-product pages, which clearly distinguishes it from compare_products and get_service_info.

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 contains explicit 'USE THIS WHEN' and 'DO NOT USE THIS FOR' sections covering single product URLs, search/category pages, login/paywall pages, and non-product pages. It also routes exploratory use to the try_it_free sibling with a clear condition: wanting to see real output before spending anything.

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?

readOnlyHint covers the safety profile, and the description adds that the tool is free and returns a description rather than sample output. However, it does not explain what 'Free' means or characterize the returned fields beyond a short list, so behavioral detail remains thin.

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 two short sentences with no redundant schema repetition, and the alternative call is placed at the end. The leading sentence fragment 'Free.' is terse but not wasteful; minor structural polish would make it a 5.

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, read-only info tool, the description covers what the agent gets (price, network, return description) and where to go for a sample, which is sufficient to invoke correctly. It stops short of enumerating the output format, but try_it_free covers that need.

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 input schema has zero parameters, so there is no parameter meaning to document; the baseline of 4 applies. The description does not need to compensate for any parameter documentation gap.

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 the tool surfaces service-level information ('Price, network, and what this service returns') and distinguishes itself from try_it_free by offering a description rather than a sample. It is clear enough, though it leans on the tool name for the verb and leaves the leading 'Free.' slightly ambiguous.

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 routes to try_it_free when the agent needs an actual output sample rather than a description, which is a clear use-vs-alternative condition. It does not discuss compare_products or get_product_details, but their names make the boundary less critical.

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. The description adds meaningful context: 'It takes no arguments and costs nothing' and 'produced by the identical code — not a hand-written example — so what you see is what you get.' This goes beyond annotations without contradiction.

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 somewhat verbose but well-structured: it opens with the core purpose, then provides usage guidance and rationale. Every sentence adds value, though it could be tightened slightly.

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 tool with an output schema, the description fully covers what the agent needs: what it does, why it's free, what to expect, and which sibling to use instead. Nothing essential 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?

The tool has zero parameters, so schema coverage is trivially 100%. The description reinforces 'takes no arguments,' which is consistent. Baseline of 4 is appropriate since there is nothing more to explain.

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: 'Run a real extraction against one fixed sample product page and return the result.' It clearly differentiates itself from siblings like get_product_details by focusing on the free sample nature, making it unmistakable.

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 explicitly says 'USE THIS to decide whether the paid tools are worth paying for' and tells the agent to 'Use get_product_details for the URL you actually care about.' It also explains why you cannot choose the page, giving a clear when-to-use vs. alternative.

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