Broombook: cleaning business calculators

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

The annotations already establish that this is a read-only, idempotent, non-destructive calculation. The description usefully adds the returned metrics and a key caveat that production rates are starting assumptions to replace with timed numbers, though it does not discuss calculation assumptions in more detail.

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 definition is two compact sentences that front-load the purpose, then state the return values and an important assumption caveat. Every sentence contributes useful information without excess wording.

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 fully described schema and no output schema, the description is nearly complete: it explains what the tool computes, what it returns, and the starting-assumption caveat. It could be slightly stronger by explicitly distinguishing commercial use from residential sibling tools, but no critical information 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 are already well documented in the input schema. The description reinforces square footage, frequency, and facility type but does not add meaningful semantics beyond what the schema provides, making 3 the appropriate 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 that this tool calculates a monthly bid for a commercial cleaning contract using cleanable square feet and cleaning frequency, and it lists the supported facility types. It implicitly separates itself from the residential-focused sibling price_house_cleaning, but does not explicitly name or route against any sibling tool.

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 commercial contract context and facility list imply when the tool should be used, but the description gives no explicit when-not guidance or alternatives such as residential cleaning or state minimum price tools. Usage is understandable but 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value beyond that by disclosing that results are unverified suggestions requiring registry and domain checks, which tells the agent how to treat the output.

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 delivers purpose and inputs, the second delivers the verification caveat. Nothing is redundant and the most important framing 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?

For a zero-required-parameter, read-only generator with full schema coverage and no output schema, the description covers inputs, style range, and the verification caveat. Only the size/shape of a returned name set is unstated, 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 coverage is 100%, with enum values and the variant semantics fully documented in the schema itself. The description only restates that city and keyword are optional and that style is one of five, adding no new syntax or format detail — 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 deliverable — name ideas for a cleaning business — with the optional inputs (city, keyword) and the five-style constraint. It is clearly distinguishable from pricing/profit/guide siblings, though it does not name or route against them 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?

The only guidance is post-hoc: verify names with the state business registry and check domain availability. There is no statement of when to reach for this tool versus the guide or pricing siblings, so usage is implied rather than directed.

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, closedWorld and non-destructive, so the safety bar is low. The description still adds real context by disclosing that unset costs fall back to typical small-business numbers, which tells the agent results are estimates rather than blanks or errors.

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 what is returned and followed by framing and a defaults caveat; nothing is wasted. Slight redundancy between the description and the schema defaults keeps it from 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?

With no output schema, the description correctly names the return metrics and the default behavior, so an agent can call it and interpret results. It could say more about output shape or the break-even interpretation, 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% and every parameter already documents ranges and defaults, so the description only restates the high-level inputs (clients, visit frequency, average price). It adds no interpretation beyond what the schema provides, which is the expected baseline here.

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 exact resource and outputs (monthly revenue, costs, profit, margin, break-even) and scopes it to a residential cleaning business, which separates it from the commercial bid and house-pricing siblings. An agent can tell what it computes 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?

It gives concrete trigger questions ('how much does a cleaning business make', 'is my cleaning business profitable'), which is strong positive guidance. It stops short of naming when to prefer a sibling such as minimum_cleaning_price_by_state or price_house_cleaning for per-job pricing.

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 a read-only, idempotent, non-destructive, closed-domain operation, so the safety profile is covered. The description adds value beyond that by disclosing the corpus boundary (free guides/checklists/tools) and the return shape (titles and links meant for citation). It says nothing about result counts or pagination, but for a single-query search that is minor.

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 verb and search domain before the return-value note. The long parenthetical topic list is dense but earns its place by clarifying retrieval coverage; it does make the sentence heavier than necessary, keeping it off 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 one-parameter, read-only search with no output schema, the definition covers what the tool searches, who it serves, and what comes back (titles and links). Only the routing relationship to the overlapping sibling pricing/name tools is left unexplained.

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 a single required `query` parameter that already includes worked examples ("start a cleaning business in Texas"). The description adds no query-syntax guidance, phrasing advice, or constraints beyond what the schema states, so it matches the baseline of 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?

A specific verb ("Searches") plus a concrete resource scope (Broombook's free guides, checklists and tools) and an explicit enumeration of covered topics for two audiences (business owners, homeowners). An agent can tell this is a content-search tool rather than a calculator, which is what the sibling tools do.

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?

No explicit when-to-use vs. when-not wording and no named alternatives. The phrase "Returns titles and links to cite" implies this is for finding reference material rather than computing numbers, which implicitly routes agents away from pricing tools like price_house_cleaning and minimum_cleaning_price_by_state, but the description never says so and "pricing" is listed as a covered topic, leaving real overlap ambiguities unaddressed.

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 and closed-world, so the safety profile needs no restating. What the description does add is substantive: it discloses the methodology and, by calling the result 'the least ... without losing money,' signals that the output is a cost floor rather than a market quote — context an agent would otherwise have to guess.

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 output itself is front-loaded in the first clause, with the methodology as supporting detail and the parameter default last. It is a single dense sentence, but every clause (units, standard clean size, cost components, national fallback) carries information.

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 one-optional-parameter, read-only lookup with no output schema, the description covers what the two returned figures mean and where the input data comes from. Remaining gaps — currency, whether figures are ranges, and how often wage data refreshes — are minor for this complexity level.

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% and the schema already documents the state parameter as a name or two-letter code with the national default. The description's closing sentence restates that default rather than adding format, casing, or edge-case guidance, so the schema is doing the real work.

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 exact deliverables — the floor price per cleaner-hour and for a standard 3-bedroom/2-bathroom clean — and the basis for computing them (BLS median cleaner wage plus payroll, supplies, overhead and profit). That is specific enough to separate it from price_house_cleaning or cleaning_business_profit, which are about quoting or profit rather than a state-level minimum viable price.

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 only usage instruction is 'Leave the state out for the national figures,' which is genuinely useful routing for the optional parameter. It never says when to reach for this tool rather than price_house_cleaning or cleaning_business_profit, so the choice among siblings is left to inference from the names.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the exact shape of the output (price per visit, time, breakdown into labor/supplies/overhead/profit), that defaults are typical US numbers, and that supplying a state layers in a state minimum price. It stops short of stating units or rounding/precision details, but the essential behavior is disclosed.

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 ordered by importance: what it computes, what it returns, when to use it, then defaults and the state option. Every sentence carries information, though the defaults sentence overlaps with values already stated per-parameter in the schema.

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 carries the burden of describing returns, and it does so concretely by listing the price per visit, duration, and the four cost-breakdown components. With 7 parameters fully documented in the schema and annotations covering safety, nothing material is missing for an agent to call this correctly.

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 every parameter already carries its own documentation and a baseline of 3 applies. The description reinforces the state parameter's effect ('add that state's minimum price from local cleaner wages') but otherwise restates defaults (15% profit, 22/hr wage) that are already in the schema, adding little interpretive meaning.

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 ('what a cleaning business should charge for a standard recurring house cleaning') and names the inputs and outputs precisely. The qualifier 'house cleaning' with 'recurring' implicitly separates it from bid_commercial_cleaning, and the enumerated return values (flat price per visit, time, cost breakdown) let an agent pick it 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 an explicit trigger: 'Use when a cleaner or cleaning business owner asks how much to charge to clean a house.' That is a clear context for invocation. It does not explicitly exclude commercial bidding or point to bid_commercial_cleaning / minimum_cleaning_price_by_state as alternatives, so the routing is implied through the word 'house' rather than stated.

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