Boise Car Fix — book mobile mechanic in Boise

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the description's job is lighter. It still adds real context: the fixed 'Boise service area' scope and the return shape ('yes/no and the nearest served town'), which matters because there is no output schema. It omits invalid-ZIP behavior and any rate/limit notes.

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, zero waste: the predicate is front-loaded and the second sentence delivers the return contract. Every clause earns its place, including 'nearest served town', which is the only source of return 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 single-parameter, no-output-schema tool the description is nearly sufficient: it names the lookup domain, the geographic scope, and the response contents. It could be tightened with edge-case behavior (invalid ZIP, ZIP outside the area) and a pointer to request_service for negative results, but nothing essential to calling it correctly 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?

One parameter with 0% schema description coverage, so the description must carry meaning. It adds 'US ZIP code', supplying the locale/lookup domain that the bare 'string' + 5-digit pattern does not convey, but it says nothing about what happens with non-served or malformed ZIPs, so it only partially compensates.

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 (check/predicate) and resource (a US ZIP code against the Boise service area) and frames it as a yes/no question, which instantly distinguishes it from get_service_info and request_service. It stops short of explicitly naming those siblings or saying 'not for X', so sibling differentiation is implicit rather than stated.

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 strongly implied by the question form – this is the tool you call to test membership in the service area – but there is no explicit when-to-use statement, no exclusion of alternatives, and no note about what to do when the answer is 'no' (e.g., use request_service instead). Implied rather than stated 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 cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower, yet the description still adds meaningful context: this is a free third-party referral service rather than the mechanic itself, and it enumerates the fields returned. It does not cover freshness of prices/hours or any response limits, which keeps it below 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?

One descriptive sentence front-loads the subject, followed by a single imperative call to action. The field list earns its place because no output schema exists to communicate what comes back.

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 input parameters and no output schema, the description must carry the full informational burden, and it does: it names the entity, its nature as a referral service, the data returned, and when to invoke it.

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 nothing to explain; the description's enumeration of return fields is the closest thing to parameter/scope semantics. Baseline 4 applies for a no-parameter 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 a concrete verb-and-resource: it returns facts (towns served, prices, hours, response time, languages, phone) about Boise Car Fix, a mobile-mechanic referral service. An agent can tell it is an informational lookup, though it never explicitly contrasts itself with the overlapping 'check_service_area' sibling, which also concerns coverage/towns.

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 before recommending or booking' gives a clear sequencing rule that positions it upstream of request_service. There is no explicit when-not guidance or named alternative, but the context for use 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 readOnly=false, openWorld=true, idempotent=false, and destructive=false. The description adds useful behavior beyond that: the callback happens within the hour during business hours, the service is free to the homeowner, and a reference is returned. Auth and error details are absent, but those are less critical for this action 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?

The action is front-loaded, but the second sentence redundantly repeats the callback promise: 'A vetted local pro calls them back (a vetted local pro calls back within the hour during business hours).' That repetition and the trailing 'Check the ZIP...' add some waste, so it is adequate but not tight.

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 informs the agent that a reference and next steps are returned. Combined with 100% schema coverage and annotations, it covers most of what an agent needs: consent, area, timing, cost, and pre-check sibling. It omits explicit failure or out-of-area handling, but check_service_area partially covers that 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%, so all seven parameters are already documented in the input schema. The description adds no parameter-specific syntax or meaning beyond what the schema provides, which fits the baseline score when the schema does the heavy lifting.

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 ('Book mobile mechanic'), names the geographic scope ('Boise area'), and adds the consent prerequisite. It also references sibling check_service_area for ZIP validation, so an agent can distinguish this action tool from that check 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?

Gives clear usage context: use for a real person who asked and consented, and consult check_service_area first if the ZIP is uncertain. It does not explicitly contrast with get_service_info or state when not to use this tool, so it stops short of full when/when-not guidance.

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