Showpiece Commercial Cleaning Quotes

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 result is indicative rather than a binding quote, prices are ex GST in AUD, volume discounts are included, and the service is Sydney-only with a two-visit minimum. It does not discuss rate limits or precision of the estimate, which keeps it short of 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?

Four short sentences, front-loaded with what is returned and its caveat, then input guidance, then the escalation path. No filler and no repetition of schema content.

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 still characterizes the return value (monthly range, AUD, ex GST, discount-inclusive) and flags its non-binding nature. Combined with full schema coverage and annotations, an agent has everything needed to call it correctly and interpret the result.

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 is already documented, including the note that hours_per_week is more accurate than area_sqm. The description restates that preference and the area-or-hours choice but adds no format, default, or constraint 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?

States a specific verb and resource: returns an indicative monthly price range in AUD ex GST for recurring commercial cleaning in Sydney, including volume discounts. It explicitly distinguishes itself from a quote and from the sibling request_site_inspection, so 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?

Gives explicit input guidance (provide area_sqm, or hours_per_week if known because it is more accurate), a hard eligibility constraint (Showpiece cleans from 2 visits per week), and a named next step (use request_site_inspection to proceed). The when-to-use and when-to-escalate paths are both covered.

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 safety is covered. The description adds the content scope (credentials, quoting model) and the precondition-style guidance, but says nothing about return format or length, leaving some behavioral gaps for an info tool with no output schema.

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 lists the facts returned, the second gives the call ordering. Content is front-loaded and no sentence is wasted.

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, no-output-schema info tool, the description is nearly sufficient: it tells the agent what facts come back and when to call it. Slightly short of full marks because an agent cannot tell whether the response is structured text or prose, which matters when composing a follow-up.

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 there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies a parameterless lookup by describing fixed facts about one business.

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 resource and enumerates the content: site types, service area, compliance credentials, quoting process, tied to a named business (Showpiece Commercial Cleaning, Sydney). It is clear what the tool returns, though it does not explicitly contrast itself with estimate_cleaning_price or request_site_inspection.

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?

"Call this first to check Showpiece is a fit" gives concrete sequencing guidance that positions it ahead of the pricing and inspection siblings. It lacks explicit when-not conditions or named alternatives, but the ordering instruction is actionable.

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 a non-destructive, idempotent write with no open-world access, so the safety profile is covered. The description adds genuine context beyond that: this triggers human follow-up by a team member and creates no booking or contractual obligation, plus a consent requirement. It does not say what the caller receives back or how duplicate submissions are handled, so it is good but not rich.

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 with the action first, then the precondition, then the scope disclaimer. Nothing is redundant and the ordering front-loads the most decision-relevant 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 16-parameter submission tool with a real-world side effect and no output schema, the description covers what the call does, the consent requirement, and what it does not commit to. It omits expected turnaround or what the caller gets back after submitting, which would be helpful for a tool that hands off to a human.

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 94%, so the schema itself documents nearly every field, including consent, enums, and ranges. The description adds only the 'pass their real contact details' guidance, which reinforces data quality but doesn't explain individual parameters, matching the baseline for high-coverage schemas.

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: submits an enquiry so a Showpiece team member arranges a site inspection and a firm quote. The 'firm quote' framing implicitly separates it from the pricing-estimate sibling, but it never names estimate_cleaning_price, so differentiation is left partly to inference.

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 precondition ('Only call this once the person has agreed to be contacted') and clear exclusions ('does not book anything or commit anyone to a contract'). It stops short of naming estimate_cleaning_price as the earlier step or describing when in a conversation flow to invoke this versus that tool.

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