LeadProof

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

Annotations only declare the mutation profile (readOnly=false, idempotent=false, openWorld=true); the description adds the genuinely novel behavior that a PERSON must open the link and that nothing is charged until approval. That human-in-the-loop, deferred-charge semantics is exactly the context annotations cannot convey.

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?

Four tight sentences, front-loaded with the action and its return, then the approval caveat, then the email prerequisite, then the returned fields. The email sentence partially overlaps the schema's email description, a minor redundancy.

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 carries the return contract itself (order id, approval link, order-status link, status token) and explains the payment-approval flow. Nothing an agent needs to call and follow up on this mutation 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 description coverage is 100%, so all five parameters including the min_reviews enum and qty bounds are already documented. The description only adds a prioritization nudge ('Ask for the delivery email first') and does not add format or constraint meaning beyond the schema, matching the baseline 3.

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 ('Creates the order') and immediately names the distinctive output ('returns a PayPal approval link'), which separates it from siblings like get_checkout_link and quote_lead_list. An agent can identify this as the order-creation step 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 a clear prerequisite ('Ask for the delivery email first') and routes the agent to get_order_status via the status token. It implies the workflow position but never explicitly contrasts with siblings such as get_checkout_link or quote_lead_list, so when-not-to-use remains unstated.

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, idempotentHint=true, and destructiveHint=false, so safety is covered. The description's one added behavioral fact — 'Nothing is created until they order' — is genuinely useful and consistent with those hints, but it omits link expiration, price-locking, and whether the link is reusable.

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 what the link is, then the flow, then the usage cue. Minor inefficiency: it describes the recipient's experience rather than framing it as a returned artifact, but nothing 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?

No output schema exists, and the description does signal the return type (a link URL) as well as the side-effect profile. It stops short of covering link lifetime or how the returned link relates to a later order lookup, which an agent would want given the create_order/get_order_status siblings.

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%, with clear per-parameter docs including the qty range, location format, review thresholds, and the cost tradeoff for higher min_reviews. The description adds no parameter meaning, so the 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?

The description states a concrete deliverable (a leadproof.co link with the list preconfigured) and describes the end-to-end flow the link enables. It distinguishes itself implicitly from create_order by noting nothing is created until the person orders, but it never names a sibling explicitly. Clear purpose, weak sibling differentiation.

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 this when they prefer to finish in a browser' is a real usage cue, but it gives no explicit alternative (e.g. create_order for immediate/API purchase) and no when-not condition. With five sibling tools that also deal with leads and orders, the routing guidance is implied rather than specified.

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, idempotent, and non-destructive, so safety is covered. The description adds genuine value beyond them by enumerating the possible statuses and noting that 'delivered' includes a download link, which shapes how the agent interprets the response.

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 sentences, front-loaded with the status enumeration followed by the required inputs. Every clause earns its place with no filler.

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 simple two-parameter read tool with no output schema, the description supplies enough context: the possible results and where the credentials come from. It could mention error behavior for invalid tokens, but 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?

Schema coverage is 100%, so the schema already documents the order_id format and token requirements. The description only adds the origin of the values (both come from create_order), which is useful provenance but marginal over the schema itself. 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?

The description names a specific verb (get) and resource (order status), then enumerates the exact status values it returns. It explicitly ties the tool to create_order, cleanly distinguishing it from the other siblings like get_checkout_link and get_pricing.

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 states the prerequisite clearly: the order must have been created with create_order, and it requires the order_id and status_token that create_order returned. It doesn't explicitly contrast against alternatives, but the sequencing context (after create_order) is unambiguous.

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 destructiveHint=false, so the safety profile is fully covered by structured data. The description adds that pricing includes multipliers and quantity limits, useful content context, but says nothing about permissions, rate limits, or caching beyond what annotations imply.

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 compact sentences: the first front-loads the payload contents, the second gives the call condition. No filler and nothing redundant with the schema or annotations.

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 parameters and no output schema, the description is the only source on return values, and it covers the key fields (tiers, multipliers, limits, list contents). It is nearly complete, though it could confirm whether the response is static or customized per account.

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; the baseline for a no-parameter tool applies. The description appropriately spends its words on return content instead of parameters.

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 enumerates the concrete content returned — price tiers, review-filter multipliers, quantity limits, and delivered-list contents — which is specific and distinguishable from quote_lead_list. The verb is implied by the name rather than stated, but the resource and scope are unambiguous.

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?

Explicit trigger: 'Call this before quoting if the person wants to compare options,' which establishes timing relative to the quoting siblings. It does not name quote_lead_list directly or state a when-not condition, 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 declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: the rows are fake, using reserved example domains, and the response also includes a column reference. It does not say anything about pagination or row limits beyond the schema's maximum of 10.

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?

A single dense sentence that front-loads what is returned and appends the crucial caveat that the data is not real. Nothing is wasted, though the parenthetical is slightly heavy.

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?

There is no output schema, so the description must convey the return shape, and it does: rows in the exact delivered format plus a column reference. Combined with a fully documented single parameter and rich annotations, an agent has enough to invoke and interpret this correctly; only the relationship to real-data tools is left to inference.

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% — count is fully documented with default, min and max — so the schema carries parameter meaning. The description adds nothing about the count parameter, which is fine given full coverage, and 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 states the resource concretely — illustrative lead rows in the exact delivered format plus a column reference — so an agent knows it returns sample data, not a computation or a mutation. It is clear on its own but never names or contrasts itself with the sibling quote_lead_list, which is the tool that returns real leads.

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: the parenthetical '(placeholder businesses on reserved example domains, not real leads)' hints this is for inspecting format before ordering or quoting, and implicitly points away from real-data tools. There is no explicit when-to-use, no prerequisites, and no named alternative.

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, idempotent, non-destructive, closed world), so "Nothing is created" is largely redundant. The description does add value by disclosing the response content — the amount charged, what is included, and delivery terms — since there is no output schema. It stops short of quoting validity, expiry, or currency details.

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: the first front-loads what is priced and from which inputs, the second covers output and the no-side-effect guarantee. No filler.

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 simple read-only quoting tool with full schema coverage and annotations that already declare safety, the description covers inputs, output content, and side-effect status. Remaining gaps (price validity, whether the quote locks in a rate) 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?

Schema description coverage is 100%, so the schema already explains qty ranges, location format, and the min_reviews cost trade-off. The description only restates the parameter list (business types, locations, quantity, optional review bar) without adding syntax or semantics beyond the schema, so the 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 specific verb and resource ("Exact price for a lead list") plus the inputs that drive the quote, which separates it from the generic get_pricing sibling and from create_order. An agent can tell what it produces 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?

"Nothing is created" implicitly positions this as the pre-purchase step before create_order, but no alternative is named and no explicit when-to-use/when-not guidance is given (e.g. quote vs. sample leads vs. pricing). Usage must be inferred from the tool name and siblings.

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