Inescapable Detail

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

Adds context beyond the annotations: payment is collected at the visit rather than by the tool, and David texts the customer to confirm, which signals an out-of-band follow-up side effect. It does not cover failure handling (e.g. slot taken between find_open_times and booking) or what the call returns, so it is strong but not complete.

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, front-loaded with what happens and the precondition before the mechanical instructions. No repetition of schema content and nothing 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 an 8-parameter mutation with no output schema, the description covers the precondition, the date/block source, the payment model, and the package special case. It is silent on what happens if the booking fails or how confirmation reaches the agent beyond the customer text, which is a modest 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 coverage is 88%, so the baseline is 3, and the description earns a bump by adding a real cross-field rule the schema never states: for service "package" the block represents the whole day and you should send "Morning". The remaining parameters (name, phone, address, size, gate_or_parking) are left entirely to the schema.

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?

Opens with a specific verb and resource plus scope: "Books one visit, paid at the visit." It also functionally separates itself from the siblings by making find_open_times the source of date/block, so an agent knows this is the write step and find_open_times is the lookup step.

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 gating condition: only when the person asked you to book and confirmed every field. It also names the prerequisite lookup (pick a date and block from find_open_times) and the special case that applies when service is "package".

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 genuinely non-obvious domain behavior — morning/afternoon windows, Mon/Wed/Fri mornings-only, Saturday closed, and that whole_day filters the result set to fully-open days. It stops short of saying what a returned entry looks like (per-day? per-slot?).

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, front-loaded with the core purpose before the schedule constraints and the whole_day rule. The middle semicolon chain of opening rules is dense but each clause is operational information an agent cannot infer, so little 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 carries the return-value burden and mostly meets it — it implies the result is a list of days (or days/times) that are open, filtered by whole_day. It is complete enough to call correctly, though the exact shape of a returned slot versus a returned day remains implicit.

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 both parameters are already documented, including the whole_day rationale and the days maximum/minimum. The description adds only the downstream effect of whole_day ('only days with the whole day open are listed') and says nothing extra about the days window beyond the schema's default of 14. 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+resource ('Open visit times in the next days') plus concrete scope (Jacksonville time, next N days). The business-hours rules make it unmistakably a read-only availability lookup, distinguishing it from book_visit and get_services without needing to name them.

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 clear conditional rule for switching behavior: 'Set whole_day true for The Full Package or more than one car.' This tells the agent exactly when to use which mode, though it never states the implied relationship to book_visit (e.g., call this first, then book) or any exclusions.

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 useful behavioral context about price semantics: US dollars, today's prices, and all-inclusive pricing that covers stains, sand, pet hair, and smells. However, it does not discuss return shape or variability beyond that.

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 concise sentences, front-loaded with the core purpose and followed by a clarifying pricing note. Every sentence earns its place, with no filler or repetition.

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 lookup tool with no output schema, the description sufficiently explains what is returned: a menu of services with current USD prices and inclusive pricing notes. A minor gap is that it does not indicate whether the menu is static or varies by location or service category, but overall it is fit for purpose.

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 has zero parameters, so parameter semantics are not applicable and the baseline is 4. The schema is trivially complete, and the description correctly does not invent parameter details.

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: a menu/list of services with today's prices in USD, and it clarifies that listed prices are all-inclusive. It does not explicitly contrast itself with the scheduling siblings (book_visit, find_open_times), but the purpose is unambiguous.

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 explicit guidance on when to call this tool versus the siblings, nor any prerequisites or exclusion conditions. The agent can infer that this is the pre-booking price lookup, but that inference is not stated.

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