11FGB Cleaning Tools

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

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing safety. The description adds behavioral context by noting the tool 'does not recommend brands' and that 'product-label directions always take precedence,' which are practical limitations not covered by annotations.

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 sentences with no fluff. It front-loads the usage trigger and includes a necessary caveat, making every word earn 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?

Given the tool's complexity (10 parameters, output schema) and strong annotations, the description covers the core purpose and a critical limitation ('product-label directions always take precedence'). It does not explain how to choose among product categories or cleaning types, but schema enums and defaults mitigate this 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 only 20% (2 of 10 parameters have descriptions). The description partially compensates by outlining the output types (ready-to-use solution, concentrate, water, generic container quantities) but does not explain individual parameters. Parameter names and enums are mostly self-explanatory, justifying a mid-range score.

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 tool provides 'a planning estimate for ready-to-use cleaning solution, concentrate, water, or generic container quantities across one or many jobs.' This specific verb-resource pairing distinguishes it from sibling tools that estimate cleaning time/crew or cost, leaving no ambiguity about its 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 description opens with 'Use this when a user needs...' which gives explicit conditions for invoking the tool. However, it does not name alternatives or explicitly state when not to use it, though the sibling context makes this implicit.

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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds context beyond these by clarifying that it estimates workload only, not availability or price, and lists supported property types. This gives the agent a clear behavioral boundary without contradicting the annotations.

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 exceptionally concise—two sentences with no filler. It front-loads the primary usage case, then adds property type coverage and exclusions. Every sentence 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?

Given the output schema exists and annotations provide safety traits, the description covers the essential aspects for tool selection and general invocation. It communicates what the tool does, when to use it, and what it does not do. However, the lack of parameter guidance slightly reduces completeness, but overall it is adequate for a read-only estimation 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?

The description provides no information about the 8 input parameters. With schema description coverage at only 13% (only postal_code has a description), the agent must infer parameter meanings solely from the schema itself. This is a significant gap for parameters like property_type, square_feet, condition, and cleaning_type, which are central to the tool's function.

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 tool's purpose: to estimate cleaning time and crew size. It uses a specific verb ('estimate') and resource ('cleaning time and crew'), and explicitly differentiates from cost or availability tools by stating it is 'not worker availability or a price quote'.

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 provides explicit usage guidance: 'Use this when a user asks how long a cleaning job may take or how many cleaners are needed.' It also gives a clear when-not boundary by stating it does not estimate worker availability or price. While it does not name alternative sibling tools, the scope is sufficiently distinct.

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 behavior. The description adds meaningful context: it is a 'free planning estimate' and warns 'Do not present it as a binding quote,' plus it mentions returning a visual report. This goes beyond the 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 concise—two sentences—with the use case front-loaded in the first sentence and key output/caveat in the second. Every word contributes value, with no 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?

Combined with the output schema and annotations, the description adequately covers the tool's core behavior and when to use it. However, it lacks detailed parameter guidance, which is partially mitigated by the schema but still leaves room for more completeness given the tool's 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 only 20%, so the description must compensate for the 10 parameters. It only indirectly references the property_type enum (house, apartment, condo, townhouse) and provides no guidance on other parameters like pets, add_ons, condition, or frequency. This is insufficient for low schema coverage.

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 tool estimates cleaning costs for US homes (house, apartment, condo, townhouse), distinguishing it from sibling tools like estimate_office_cleaning_cost. It also specifies the output (price range, labor hours, etc.), making 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?

The description explicitly says 'Use this when a user wants a free planning estimate for cleaning a US house...' which is clear guidance. However, it does not explicitly mention alternatives or exclusions (e.g., for office cleaning), relying on sibling names to imply differentiation.

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 indicate read-only, idempotent, and non-destructive behavior. The description adds complementary behavioral context by detailing the return content ('per-visit and monthly ranges, labor, crew, schedule assumptions, and a visual report') and clarifying that it is non-binding and free, which goes beyond the annotations.

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 a compact two-sentence structure that front-loads the primary use case and includes an exclusion. Every word adds value, with 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?

Given the tool has an output schema and annotations, the description sufficiently covers the essential context: scope (commercial/office), geography (US), cost (free), type of output, and key disclaimer. It is complete for an estimation tool with these structured aids.

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 only 10%, and the description does not explain any of the 10 parameters or how they affect the estimate. It only vaguely mentions 'schedule assumptions,' failing to compensate for the low schema coverage. Most parameter semantics must be inferred from names/enums alone.

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 tool provides a 'free office or commercial cleaning budget estimate in the United States,' which is a specific verb and resource. It distinguishes itself from the residential sibling tool by explicitly excluding residential cleaning.

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 says 'Use this when a user wants a free office or commercial cleaning budget estimate' and includes 'Do not use for residential cleaning or present it as a binding bid.' This gives explicit when-to-use and when-not-to-use guidance, effectively differentiating from alternatives.

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