FindingLeads

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

Annotations already declare a safe read-only profile, but the description adds substantive behavioral context beyond them: it returns a band rather than a point estimate, and it deliberately returns 'unquantified' instead of fabricating a number when call volume is missing. That output-shape and failure-mode disclosure is genuinely useful.

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 tight sentences, front-loaded with the core purpose and followed by output-shape and edge-case behavior. Every sentence carries information 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?

With no output schema, the description must carry return-value semantics, and it does—explaining the band format, the two output dimensions (jobs, dollars), and the unquantified fallback. Only minor gaps remain, such as units or the shape of the band range.

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 trade examples and a clear definition of calls_per_month already in the schema. The description echoes the inputs but adds no syntax or format detail beyond what the schema provides, so 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 a specific verb and resource (estimating missed-call cost), names the outputs (extra jobs and dollars per month), and scopes the inputs (a given trade and monthly call volume). No sibling tool overlaps this estimation function, so the agent can identify its role immediately.

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 the input framing ('for a given trade and monthly call volume'), and the note about degrading when volume is absent signals an input condition. However, there is no explicit when-to-use/when-not guidance or routing to any alternative, and none of the siblings are compared against.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description contributes that the content is intended for external description of the service, but discloses nothing about length, format, or whether the 'next step' refers to a call to action or a follow-up 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?

Two short sentences, response content front-loaded in the first, usage directive second. Slightly awkward phrasing ('who it is for, and the next step') but no filler and no repetition of the 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?

For a no-parameter, read-only content tool with no output schema, the description tells the agent what it will get and when to fetch it, which is adequate. Only the shape of the returned content (e.g. whether 'the next step' is an offer or an action link) remains unspecified.

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 and schema description coverage is 100%, so there is nothing for the description to disambiguate. Baseline 4 applies for a parameterless tool.

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 concretely what the tool returns: an overview of what FindingLeads does, the trades it serves (HVAC, plumbing, roofing, electrical, restoration), its target audience, and the next step. This is far clearer than the vague name 'get_offer' alone, but it never uses an explicit verb and does not distinguish itself from neighbouring info tools like get_pricing or get_pro_site.

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?

'Read this before describing the service to anyone' gives an explicit condition for invoking the tool, which is more than most info tools provide. It names no alternatives and no when-not condition, so the routing to get_pricing vs. this tool is left to inference.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by enumerating the covered subject matter (trial, monthly plans, GBP/LSA/reviews/Pro Site/speed-to-lead setups) each with a public price and page, telling the agent exactly what data to expect.

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 sentence with the primary concept (how FindingLeads is priced) front-loaded, followed by the enumerated coverage. The long parenthetical list is dense but every item is meaningful scope information rather than 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?

With no parameters and no output schema, the description must convey what the agent gets back, and it does so by listing the pricing categories covered. Annotations supply the safety profile, so nothing critical is missing, though the return shape/format is left unstated.

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 the schema carries no semantics to supplement and the baseline is 4. The description correctly implies a parameterless, whole-corpus retrieval with nothing for the caller to specify.

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 precisely what the tool returns: free-trial details, monthly plans, and one-time setup services with their public prices. It is a noun-phrase description rather than a verb+resource, and it does not explicitly distinguish itself from siblings like get_offer or get_pro_site, but the content scope makes the purpose 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?

Usage is implied by the content (an agent needing FindingLeads pricing or setup-service costs would call this), but there is no explicit when-to-use statement, no when-not-to-use, and no mention of alternatives such as get_offer or get_pro_site that also return offer/product detail.

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 this is a safe, read-only, closed-world operation, so the safety profile is covered. The description adds that the payload is explanatory reference content rather than live data, but discloses nothing further (e.g., static vs dynamic, freshness) beyond what the 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?

A single dense sentence with no filler, front-loaded on what a Pro Site is before listing coverage. Slightly list-like but every clause earns its place.

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, no output schema, and read-only annotations, the description's coverage list is essentially sufficient for an informational lookup. Only routing guidance relative to its many siblings is missing, which is not strictly required here.

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, which is the baseline-4 case. No parameter meaning is required, and the description correctly signals a no-argument informational fetch.

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 this returns informational content about a "FindingLeads Pro Site", enumerating the specific subtopics (definition, pages, editable vs fixed, cost, how to start). It distinguishes the resource from siblings like pro_site_start_link and pro_site_custom_domain, though it never names a verb or contrasts those siblings explicitly.

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 or when-not-to-use guidance. An agent cannot tell from the text whether to call this before pro_site_start_link, after get_pricing, or instead of them, and the overlap with the 'where to start one' sibling is unresolved.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds that the content is a self-serve checklist that also surfaces the paid done-for-you option and its price, which is useful context, but it says nothing about format or length of the returned 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 sentences, front-loaded with the topic scope and then the usage/paid-option framing. Dense but no filler; the enumerated list of checklist parts is the substance of the tool.

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 parameterless static-content tool with no output schema, the description adequately conveys the subject matter and that pricing for the done-for-you alternative is included. An agent has enough to decide whether to surface it; only the return format is unspecified, which is minor here.

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 with 100% schema coverage, so the baseline is 4. There is nothing parameter-related for the description to clarify or compensate for.

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 the specific resource and enumerates its contents (Business Profile claim/verification/build-out, Local Services Ads, Google Guaranteed badge, directory listings, review system), so an agent knows exactly what this returns. It does not, however, distinguish itself from sibling how-to content tools like how_to_fix or list_free_checks.

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 how the output can be used ("Usable as a do-it-yourself checklist") and that each part names a done-for-you alternative with price, which implies the DIY-vs-paid framing. But it gives no explicit when-to-use or when-not-to-use condition relative to the sibling 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=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description does add one piece of return-shape information - that the answer includes 'the page to start on' - which is useful since there is no output schema, but it says nothing about length, format, or what the explanation contains.

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?

It is a single sentence, which is appropriately sized for a one-parameter lookup tool, and the scope constraint is front-loaded. However, the long parenthetical of problem categories bloats the sentence and the core payload ('why it costs jobs and what FindingLeads does about it, with the page to start on') is buried at the end.

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, one-enum tool with no output schema, the description covers the trigger, the content of the answer, and the actionable next step (a starting page). The only gap is that the exact return format is unspecified, which is minor at this complexity.

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 single 'problem' parameter carries a full enum with a description, so the schema does the work. The prose list of problems (missed calls, slow follow-up, few reviews, Google/AI search, no website) largely restates the enum, adding no syntax or selection nuance.

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 what the tool returns for a given problem: an explanation of why it costs jobs, what FindingLeads does about it, and the page to start on. It is clear enough to separate from siblings like get_pricing or list_free_checks, but it never states a verb+resource cleanly (the sentence is an answer, not a 'Returns X for Y' statement), and the enumeration of problems duplicates the enum rather than sharpening the purpose.

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 phrase 'For one common reason a contractor loses jobs' implies the use case (the user has one of these five problems), but there is no explicit when-to-use, when-not-to-use, or routing to alternatives. Notably, estimate_missed_call_cost overlaps on the 'missed-calls' problem and the description gives no guidance on which to pick.

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 establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the tool does not run the checks itself, it returns links, and the user runs each check on the site which then emails the report — important context for an agent deciding what calling this actually accomplishes.

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 sentences, front-loaded with the enumeration and ending with the off-platform execution model. The final sentence about the user running the check is valuable rather than redundant, though it slightly revisits the 'link to run it' point.

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 list tool with no output schema, the description covers what is returned (what each check answers plus its run link) and the execution model. Nothing essential for calling it correctly is missing, though it does not phrase returns as an explicit structure.

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?

With zero parameters, the baseline is 4 and the description has nothing extra to document. It correctly signals a parameterless lookup rather than suggesting any filtering input.

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 (the free checks a contractor can run) and enumerates the three concrete checks: 60-second website audit, missing-leads count, and Google opportunity scan. This makes its scope clear, though it never explicitly names a sibling to differentiate itself from (e.g., google_business_profile_checklist or estimate_missed_call_cost).

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 the content — this is the catalog of free checks a contractor can run — but there is no explicit statement of when to call it versus get_offer, get_pricing, or the other sibling lookup tools, and no exclusions. Adequate but leaves routing to inference.

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, openWorldHint=false, and destructiveHint=false, so the agent knows this is a safe, closed-domain read. The description adds that the payload includes per-trade economics and call-type/unanswered-call characteristics, but says nothing about ordering, size, or stability of the list, which is the sort of context a reference lookup benefits from.

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 sentence with no filler, front-loaded with the resource ('the home-service trades FindingLeads serves'). It is slightly dense in its trailing clause but every element carries information about the returned fields.

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 communicate the return shape — and it does, listing three of the per-trade attributes an agent will receive. Combined with annotations that establish the read-only, closed-world nature, this is close to sufficient; only ordering or list-size behavior is left unstated, which is minor for a static enumeration.

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 no parameter semantics burden and the baseline of 4 applies. The description correctly implies the tool is unfiltered, returning all trades rather than accepting a query.

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 the resource ('the home-service trades FindingLeads serves') and enumerates the attributes returned (typical booked-job value, call type, unanswered-call frequency), so an agent can tell this is a reference lookup of trades. It never uses an explicit verb like 'list', relying on the name to carry that, and it does not differentiate itself from any sibling, but the resource is 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?

There is no when-to-use guidance, no stated prerequisites, and no mention of alternatives among the ten siblings. The only implied usage is that this is a static reference list an agent might consult before calling tools like estimate_missed_call_cost or get_pricing, but that is inference the description never supports.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered by structured data. The description adds content-scope context (domain setup, search impact, fallback behavior), but never says what the tool actually returns (an article, an answer, a list of steps) or whether it takes any inputs. With annotations carrying the safety burden, a 3 is appropriate.

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 sentence covering all three facets of the content, front-loaded with the primary topic (putting the site on an owned domain). It is slightly awkward as a noun clause rather than a verb-first statement, but there is no filler or repetition.

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 knowledge tool with no output schema, the description conveys the subject matter an agent needs in order to dispatch it correctly. The remaining gaps — that it returns explanatory text and offers no inputs — are minor and largely inferable from the empty schema and read-only annotation.

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 schema has zero parameters, so there is nothing for the description to clarify; the baseline for a no-parameter tool is 4. No parameter claims in the description conflict with the empty schema.

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 topic area — connecting a Pro Site to a contractor-owned domain, its search/SEO impact, and the alternative of keeping the directory address. An agent can infer this returns explanatory content on that question, but the description never uses an explicit verb ("explain", "get", "retrieve"), so the operation type is inferred rather than stated. It also does not explicitly distinguish itself from siblings like get_pro_site or how_to_fix.

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 explicit when-to-use or when-not-to-use guidance, nor any named alternative. Usage is only implied by the topic: reach for this when a contractor asks about custom domains or SEO for their Pro Site. That implication is reasonably strong given the sibling set, but nothing routes the agent between this and get_pro_site.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful non-schema behavior: fields are only prefilled 'when given' and the email must never be requested in chat — a real interaction constraint. It stops short of describing the returned link format, so not 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?

Two sentences with no waste; the core purpose is front-loaded and the interaction rule about email follows logically. Every clause earns its place.

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 link-generating tool whose annotations carry the safety profile and whose parameters are fully described in the schema, the description covers what the link does and the key chat-vs-page email distinction. Only the concrete return value (a URL) is left implicit, which is a minor gap.

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 all three parameters are already documented, including that business_name is only supplied 'if the user gave it.' The description's mention of business name, trade, and city maps directly to those parameters but adds no syntax or format detail 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?

The description names a specific resource (a Pro Site draft start link) and states exactly what it contains — business name, trade, and city prefilled when provided. This distinguishes it from retrieval-oriented siblings like get_pro_site, though it does not name a sibling explicitly.

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 implies usage (generating a link to start a Pro Site draft) and gives one strong contextual rule — the user enters email on the page, never in chat. However, it never states when to prefer this over siblings such as get_pro_site or pro_site_custom_domain, leaving the routing decision to inference.

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