Corpus Car Fix — book mobile mechanic in Corpus Christi

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description usefully adds the return shape ('yes/no and the nearest served town'), which is meaningful since no output schema exists, and its closed-world framing matches openWorldHint=false.

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 with zero filler, front-loaded as the core question with the return contract immediately following. 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 single-parameter read-only lookup, the description covers intent, input domain, and return values, and the annotations cover safety and world assumptions. Nothing an agent needs to invoke 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?

Schema description coverage is 0%, so the description must carry the burden; it partially does by specifying 'US ZIP code', which scopes the value to a 5-digit US format consistent with the schema pattern. It does not explain error behavior for malformed or non-US inputs, so it adds only marginal 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?

The description states a precise verb (check) and resource (US ZIP code against the Corpus Christi service area), phrased as a direct question that an agent can map to an intent. It is clearly distinct from get_service_info and request_service, though it does not name 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?

Usage is implied by the question form — this is a lookup to run when you have a ZIP and need a yes/no answer — but there is no explicit when-to-use, when-not-to-use, or routing guidance toward get_service_info or request_service for follow-up actions.

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 (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower; the description adds the non-obvious framing that this is a free referral service rather than the mechanic itself, which prevents an agent from treating it as a transactional endpoint. It does not disclose data freshness or whether prices are current.

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 the subject front-loaded and an explicit call-to-action at the end; the colon list of return fields is efficient. Slightly packed, but 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?

With no output schema, the description compensates by enumerating the returned fields (towns served, prices, hours, response time, languages, phone), and with zero parameters there are no input unknowns. An agent has everything needed to call it 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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline is 4. Nothing in the description misleads about inputs.

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 (facts about Corpus Car Fix) and enumerates the exact data domains returned: towns served, prices, hours, response time, languages and phone. It is clearly a read-only info lookup rather than the booking or coverage-check siblings, though it never names those siblings to sharpen the contrast.

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 an explicit sequencing rule that positions the tool ahead of a booking step, implicitly pointing to request_service as the next action. It stops short of stating when NOT to use it or naming check_service_area as the alternative for coverage questions.

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 non-read-only, open-world, non-idempotent, non-destructive behavior, so the bar is lower; the description still adds real value by stating the callback window (within the hour during business hours), that it is free to the homeowner, and that a reference is returned. It does not mention failure modes such as an out-of-area ZIP rejection.

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?

Front-loaded with the core action and free of filler, but the second clause repeats the first ('A vetted local pro calls them back (a vetted local pro calls back within the hour during business hours)'), wasting a parenthetical on restatement. The prerequisite check sits appropriately 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?

No output schema exists, and the description compensates by saying a reference is returned plus what happens next. With consent requirements, the ZIP pre-check, and the callback promise all covered, the main remaining gap is what happens when the ZIP is outside the service area.

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 the schema already documents all seven parameters including formats and optionality. The description adds only an implicit consent/real-person constraint on name and phone, which is marginal beyond the structured data; 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?

Names a specific verb and resource ('Book mobile mechanic') plus a geographic scope (Corpus Christi area) and the immediate outcome (a vetted pro calls back). It distinguishes itself from check_service_area by naming that sibling as a pre-check, though it says nothing about how it differs from get_service_info.

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?

Explicitly bounds usage to 'a real person who asked for it, with their consent' and routes the agent to check_service_area first when the ZIP is uncertain. That is clear when-to-use guidance, but the agent gets no guidance on when to prefer get_service_info or check_service_area over this tool.

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