TN Appliance Exchange — appliance repair

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

Annotations establish a mutating, non-idempotent, non-destructive, open-world write, and the description adds substantive context beyond that: it creates the job, the vendor texts the customer within minutes to pick a day, and the caller must not promise an appointment time. These are behavioral facts the annotations cannot convey.

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 tight sentences with no waste, front-loaded with the action and scope, then preconditions, outcome, and a constraint. Every sentence carries distinct 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 mutating tool with no output schema, the description covers preconditions, downstream behavior, and a key constraint well, and annotations carry the safety profile. It stops short of noting what to do when the location is outside the service area, where check_service_area would be the relevant sibling.

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 46%, so the description should compensate more than it does. It reinforces the semantics of the two consent booleans (agreeing to book and to be texted) but says nothing about zip, phone, appliance_type, or problem, leaving the coverage gap partially unaddressed.

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 (Book) and resource (in-home appliance repair) plus geographic scope (Tennessee or Louisiana), which cleanly separates it from siblings like check_service_area and diagnose_appliance_problem. An agent can identify this as the booking action 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 an explicit precondition ('Only call after the person has agreed to book and to be texted') and a behavioral constraint ('Never promise an appointment time'). It doesn't name sibling tools or route between alternatives, but the when-to-use context is clear.

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 readOnlyHint=true and openWorldHint=false, and the description adds genuinely non-obvious behavior: full coverage for Tennessee and Louisiana, and the $50 video diagnostic fallback everywhere else. It does not mention rate limits, response shape, or whether the check is authoritative, but for a simple read-only lookup this is solid added context.

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, with the primary purpose front-loaded and the exception/fallback immediately following. 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?

There is no output schema, so the description must explain outcomes, and it does so for both branches (covered vs. video diagnostic). It could be marginally more explicit about what the covered case returns or implies, but nothing essential for correct invocation 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 100% ('5-digit US zip code') and there is a single required parameter, so the schema already carries the semantics; baseline 3 applies. The description's mention of 'US zip code' adds no format detail beyond what the schema states.

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 ('check') and resource ('service area' for a US zip code), plus the exact business rule that determines the answer. It is easy to distinguish from siblings like book_repair or diagnose_appliance_problem, which perform different actions.

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 makes the use case clear (verify coverage before in-home repair) and explicitly describes the fallback path for out-of-area zips ('nationwide $50 video diagnostic option'), which routes the agent to an alternative outcome. It never names a sibling tool or states a when-not-to-use condition, so it stops short of a 5.

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 readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral value beyond that: it enumerates the returned content (likely causes, safe checks, safety warnings) and states a hard scope limitation ('Never returns part numbers'), which sets expectations about what the agent will not get back.

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, input guidance front-loaded after the purpose, and the output/limitation statement placed last. Efficient overall, though the opening 'Honest troubleshooting from working appliance technicians, grounded in real completed repairs' leans promotional rather than informative.

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 usefully explains what comes back (causes, safe checks, warnings) so the agent knows the shape of the response. Remaining gaps are minor — no guidance on result trust level or follow-up actions — for a read-only diagnostic 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?

Schema coverage is 80% and the schema already carries descriptions for model, symptom, appliance, and error_code. The description names the same five inputs and marks brand/model/error_code as optional ('if known'), but adds no formatting, syntax, or example detail beyond what the schema provides — baseline 3 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?

The description states a specific verb and resource — troubleshoot/diagnose an appliance problem from real repair data — and is obviously distinct from booking or business-info siblings by nature, though it never names an alternative tool explicitly. An agent can tell what this tool is for 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?

It tells the caller what to supply ('Give the appliance and symptom, plus brand, model and any error code if known'), which is useful invocation context, but gives no when-to-use vs when-not guidance relative to siblings like book_repair (e.g., diagnose first, book only if a repair is needed). Usage is implied rather than routed.

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?

readOnlyHint=true already tells the agent this is a safe, non-mutating, closed-world read. The description adds a genuinely useful behavioral detail — booking works by day, not time — but does not describe what the returned text looks like or how comprehensive it is. Adequate with annotations, 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?

One compact sentence enumerating the content topics; nothing is wasted and the core subject (who they are) is front-loaded. The trailing list is slightly dense but appropriate for a content-dump tool.

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-only info tool with no output schema, enumerating the covered topics (identity, service area, services, booking, policies) effectively communicates the scope of what comes back. Minor gap: no statement of format or depth of the returned content.

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, which per the rubric sets a baseline of 4. No parameter documentation is needed, and the description correctly does not invent any.

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 resource: the business's identity, service area, services, booking mechanics, and policies. It is specific about content, though 'where they serve' overlaps conceptually with the check_service_area sibling and the description never contrasts itself with that 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?

Usage is implied (fetch general company context) but there is no explicit when-to-use, when-not-to-use, or routing to siblings like check_service_area for geographic eligibility. The parenthetical about booking being day-based hints at value for book_repair, but the connection is left to inference.

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 readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: it enumerates the returned content (blurbs with links, first-name-plus-initial reviews, hashtags, profile links) and states the mandatory brand rules (no part numbers, customer info, appointment times, or 'best' claims) that constrain any post built from it.

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?

It is a single dense sentence, but the most important framing — approved, ready-to-post material — comes first, followed by the content inventory and then the filter. The long parenthetical of brand rules is justified because those rules govern how the content may be used, though the sentence is heavier than ideal.

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 must describe returns itself, and it does: it names each content type plus the governing brand rules, which is what an agent needs to know before composing a post. It omits any note on volume, ordering, or what an empty topic match returns, but for a one-parameter read tool it is largely complete.

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 100% with a single optional 'topic' string, so the baseline is 3. The description earns above that by giving concrete example values ('dryer vent', 'refrigerator', 'Louisiana') that clarify the expected granularity of the filter beyond the schema's bare 'Optional topic to filter by'.

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 resource — approved Facebook/Instagram/Google post material (press blurbs, reviews, hashtags, profile links, brand rules) — so an agent can tell it apart from siblings like get_business_info or book_repair. It stops short of naming any alternative or explicitly contrasting its scope, but the content inventory is concrete enough to identify the tool's 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?

Usage is only implied: an agent infers it should call this when it needs approved social copy, and the topic filter is illustrated with examples ('dryer vent', 'refrigerator', 'Louisiana'). There is no statement of when not to use it, nor any pointer to a sibling tool for related needs.

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