ATX Mini Split

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

No annotations, so the description carries the full burden. 'Full verified record' usefully signals that the response is complete and trustworthy versus a partial hit from search, and 'get' implies a safe read, but auth needs, rate limits, and error behavior are undisclosed.

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 sentence with the purpose front-loaded and the parameter provenance folded into a parenthetical. No wasted words.

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 lookup with no output schema, the description covers the essentials: what it returns, how to get the identifier, and which sibling precedes it. It stops short of describing response shape, but the 'full record' framing is acceptable here.

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 schema only gives type and maxLength. The description compensates by explaining where the slug comes from (search_companies or a profile URL), which is genuinely useful, but says nothing about its expected format or case sensitivity.

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 scope: a single, full verified company record. It also names the sibling search_companies as the source of the slug, so an agent can immediately tell how this differs from the search 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 parenthetical makes the usage path clear: call this after search_companies or take the slug from a profile URL. It gives clear context for when the tool applies but states no exclusions or failure conditions (e.g. unknown slug).

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?

No annotations are provided, so the description carries the full burden. It does disclose a meaningful trait — prices are 'quoted as written', i.e. unnormalized verbatim figures from contractor sites — which warns the agent not to expect canonical or comparable pricing. However it says nothing about coverage, freshness, or how results are returned, leaving the read-safety and result-shape profile unstated.

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 tight sentence with no filler and the key scoping qualifiers (installed, Austin-area, contractor-published) front-loaded. It is efficient, though the terseness leaves the action verb implicit.

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-parameter read tool with no output schema and no annotations, the description is minimally adequate: it defines the data but does not describe the return structure, how many benchmarks to expect, or freshness. With no output schema to lean on, slightly more disclosure would be warranted.

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 schema has zero parameters, so per the baseline there is nothing for the description to document. The sentence about sourcing adds interpretive context rather than parameter detail, which is appropriate for a no-arg lookup.

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 identifies the resource precisely (installed HVAC prices from Austin-area contractors' own websites) but never states the action the tool performs — no verb like 'returns' or 'list'. An agent can infer it retrieves price data, but the purpose is implied rather than stated, and the distinction from siblings like search_companies rests only on the topic noun.

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?

There is no when-to-use guidance, no condition that selects this tool over search_companies or request_mini_split_quote, and no exclusions. The description is purely a data definition with no routing signal.

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?

With no annotations the description carries full burden, and it discloses two meaningful traits: the recipient is an advertiser owned by the site's operators (a conflict-of-interest disclosure an agent should surface) and the flat price ($2,000 per unit installed). It does not say what happens after submission (confirmation, whether data is forwarded to a third party, idempotency), which keeps it from 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?

Two sentences, zero padding, with the action and the price front-loaded before the constraint. 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?

Covers purpose, the advertising relationship, pricing, and the consent precondition, which is the most important context for a lead-gen tool. But with no annotations, no output schema, and 6 undocumented parameters, the description leaves an agent without guidance on what the call returns or what the free-text params should contain.

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% across 6 parameters, so the description must compensate and largely does not. Its only parameter-relevant signal is that phone or email is expected in practice, despite both being optional in the schema; rooms, units, and city are left entirely unexplained (e.g. units bounds, rooms format).

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?

Specific verb ("Send") plus resource ("flat-price mini split quote request") plus the named recipient/advertiser, which cleanly distinguishes it from the read-only lookup siblings (get_company, search_companies, price_benchmarks). An agent knows immediately this is a lead-submission action, not a data-retrieval one.

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 a hard precondition for use: "Only when the user explicitly asks to be contacted and provides their own phone or email." That is effectively a when-not rule as well. It stops short of naming any alternative tool, but the gating condition is explicit and 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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that results are ordered by the site's published score, but omits other relevant behaviors such as pagination, default result count, or whether the operation is read-only.

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 single, front-loaded sentence with no filler. It efficiently conveys purpose, location, primary filters, and ordering.

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 annotations, no output schema, and low parameter description coverage, the description is too thin for a search tool with four parameters. It does not explain the financing filter, the limit parameter, or what the returned company records contain.

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 25%, and the description mentions only city and service filtering. The financing and limit parameters receive no explanation in either the schema or the description, leaving meaningful filter and result-size semantics undocumented.

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 and resource: finding licensed HVAC/mini split contractors around Austin TX. It also names the primary filters (city, service) and result ordering. It does not explicitly distinguish itself from siblings like get_company or price_benchmarks, so it falls short of a 5.

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: use this tool to search for contractors by city and service. However, there is no explicit guidance on when to choose this over get_company, price_benchmarks, or request_mini_split_quote, nor any stated exclusions or prerequisites.

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