WebMCP Eval

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

Goes well beyond the annotations (which only declare readOnly/openWorld/non-destructive) by disclosing the exact cost ($2 from prepaid credits), the billing boundaries (never charges a card, never starts auto-reload, failed fetches not billed), the data processors (Firecrawl and OpenAI), the privacy guarantee (no wallet keys or chat content sent, no URL history retained), and the balance precondition. This is the kind of cost and side-effect detail an agent needs before invoking a paid tool.

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?

Purpose and the 'what it is not' clause are front-loaded, followed by billing, privacy, and setup facts in dense, non-repetitive sentences. It is long but nearly every sentence carries a distinct constraint (cost, billing limits, processors, error path); only the stacked reference links add minor bulk.

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 steps in by naming the returned artifacts (observed tools, recommended tools, do-not-expose), and it covers cost, privacy, prerequisites, and failure handling. The only real gap is the undocumented `max_offers` parameter.

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 carries the full burden. It clarifies `url` ('the page to audit' and must be public HTTPS), but `max_offers` is never mentioned, leaving half the parameters undocumented anywhere. Partial compensation justifies a mid score rather than a high one.

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+resource+scope ('Evaluate one public HTTPS page URL for WebMCP readiness') and enumerates the outputs (observed tools, recommended tools, do-not-expose). It also explicitly fences off what it is not ('Not a generic HTTP client and not a third-party REST wrapper'), so an agent can distinguish it from any sibling without opening the schema.

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?

Gives clear preconditions (public HTTPS URL, prepaid wallet required) and an explicit recovery path: if balance is below $2 the tool errors and you call reload_credits. It does not state when not to reach for this over the credit siblings beyond that conditional, so it stops short of full routing guidance.

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 read-only, non-destructive, and closed-world status, so the bar is lower; the description still adds domain-specific reassurance ('Does not charge and does not create Checkout') and, with no output schema, discloses the shape of the returned data. It stops short of describing failure modes or auth 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?

Front-loaded and only four short sentences, with the read/returned-fields statement first and routing second. 'Use this to check balance' mildly restates the opening sentence, a small redundancy rather than clutter.

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 tool with no output schema, the description supplies the returned field names, the absence of payment side effects, sibling routing, and a docs link. Nothing an agent needs to call 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?

The tool takes zero parameters, so per the baseline this is a 4. The description correctly adds no parameter detail because there is nothing to parameterize.

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 ('Read') and resource ('this connected wallet') and enumerates the returned fields (account_id, hint, credits, balance). It also names the sibling reload_credits, so an agent can tell the two apart without opening a schema.

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?

Gives an explicit when-to-use ('Use this to check balance') and an explicit alternative with its trigger condition ('Use reload_credits only when the customer wants to pay'). Routing between the two siblings is fully determined by the text.

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 say readOnlyHint=false, destructiveHint=true, openWorldHint=false; the description goes further by clarifying no charge/transfer occurs, that payment happens in the human's browser, that the same connector and usr_live_ key are reused, and that no new wallet is created. The 'does not charge and does not transfer funds' claim sits in mild tension with destructiveHint=true, but it reads as disambiguation of an over-conservative hint rather than a direct 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?

Front-loaded with the action and price, followed by effect disclosure and sibling routing. 'Same connector and same usr_live_ key. Not a new wallet.' is slightly cryptic/redundant but still earns its place as scope clarification.

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-param, no-output-schema tool, it covers the return value (a session URL), the effect (no funds moved), and the next step. It omits details like session expiry or what else the response contains, which are minor.

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?

Zero parameters, so the schema carries no semantic load; the description usefully explains that the target wallet is implicit ('this connected wallet') and that the same credentials are reused.

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 (create) and resource (a $26 / 13 Stripe Checkout session URL) scoped to 'this connected wallet', which an agent can immediately distinguish from the read-only get_credits sibling.

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 the agent: 'Do not call this to read balance — use get_credits', naming both the exclusion and the correct alternative. It also implies the trigger condition (a human must open the URL and pay on Stripe).

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