Mane

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

Annotations already declare read-only, idempotent, non-destructive, closed-world, but the description adds real value beyond them: no hold, no charge, no contact, where the operator's card and cancellation rules apply, and exactly what the error response contains. That is precisely the context an agent needs before promising a user a booking.

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 tight sentences, front-loaded with the core behavior, then the non-effects, then the failure mode — no filler and nothing repeated from the schema or annotations.

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 does so: a URL to the operator's booking page with fields pre-filled, or an error enumerating open times. Nothing an agent needs to call this correctly or set user expectations 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 coverage is 100% and each param already documents its format and source (service_id from list_services, start_time from list_availability). The description only restates that the three values are filled into the link and that a bad time yields an error with that day's open times, which is marginal added meaning. 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 and resource: checks availability for a service/date/start time and returns a joinmane.com booking link pre-filled with those values. It implicitly separates itself from list_availability (raw times) and list_services (IDs) by describing the check-and-link outcome rather than a listing.

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?

Clearly frames the boundary: 'It does not book, hold the time, charge or contact anyone' and explains the booking only completes when the client confirms on joinmane.com. The failure case ('result is an error listing the open times that day') is spelled out, though it never explicitly says to call list_availability first or when to prefer this over the sibling tools.

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, idempotentHint and destructiveHint=false, so the safety profile is covered. The description still adds value by stating the profile is "public" (no private data exposed) and by imposing the exactly-one-identifier rule that the annotations do not cover.

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 filler: the returned-field list comes first, the invocation constraint second. Nothing is repeated from the title.

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, enumerating the returned fields is exactly the right compensation, and the identifier rule is spelled out. It stops short of saying what happens on error (both or neither identifier supplied), which matters given neither parameter is required.

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%, so the baseline is 3; the description earns an extra point because it states the mutual-exclusivity requirement (exactly one of slug or operator_id), which the schema does not express — both properties are optional there.

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 and resource ("Returns the public profile of one listed operator") plus an enumeration of the concrete fields returned, which lets an agent distinguish this from list_services or get_booking_link 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?

The constraint "Provide exactly one of slug or operator_id" is an invocation rule, not a when-to-use rule. It never says to use this after search_operators to hydrate a result, nor when to prefer it over get_booking_link, so usage is only implied.

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 a safe, idempotent, closed-world read, and the description adds substantial context beyond that: the availability rules applied (hours, breaks, days off, existing bookings, same-day notice), a per-slot price that may differ from list price, and the meaning of an empty result. That is exactly the extra behavioral context the annotations cannot express.

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 sentences, front-loaded with what is listed and under what rules, then the return shape, then the empty-result semantics. Every sentence carries distinct information with no redundancy.

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 carries the return contract itself and does so adequately: it names start_time format and timezone, is_after_hours, and the applicable price, plus what an empty list means. Nothing an agent needs in order to call or interpret this tool 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% and both parameters are documented there, including that service_id comes from list_services. The description adds context about the operator's local time and the single-service/single-date scoping, but no syntax or format detail beyond the schema, so the 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?

The description names a specific verb and resource ('Lists the open start times') and pins the scope to one service on one date, so the operation is unambiguous. It never names or contrasts a sibling tool (e.g. get_booking_link), which is the only thing keeping it from 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: the mention of the 'operator's booking page' and the empty-list case suggests this is a pre-booking availability probe, but it never states when to use it versus get_booking_link or list_services. There are no explicit preconditions or 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 readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds substantive behavior beyond that — only 'active' services are returned, after-hours price appears only 'when the operator set one', and services are flagged as mobile or request-only. It does not say what happens for an unknown slug or an operator with no services, which keeps it below 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 waste: the resource and scope come first, the return shape second, and the invocation constraint last where an agent will look before calling. No repetition of the title or annotations.

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 simple read-only list tool with no output schema, the description carries the necessary burden by enumerating returned fields and conditional values. Missing only edge-case behavior (empty results, invalid identifier) and any pagination note.

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% and both parameters already explain their source, so the baseline would be 3. The description adds a genuine constraint not expressed in the schema — 'exactly one of slug or operator_id' — which is critical since neither parameter is required and additionalProperties is false. It omits what happens if both or neither are supplied.

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 ('Lists the active services of one listed operator') and scopes it to a single operator, which cleanly separates it from search_operators and get_operator. The enumerated return fields make the distinction concrete rather than implied.

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 invocation context: exactly one of slug or operator_id, both sourced from search_operators. It stops short of saying when to prefer this over sibling tools such as get_operator or list_availability, but the operator-scoped framing makes that largely self-evident.

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, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely new context: only opted-in operators are ever returned, so an empty result can mean 'not opted in' rather than 'no match' — a real behavioral trait. It omits pagination, result caps, and ordering, which matters for a search 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?

Three tight sentences, front-loaded with what is listed before the return fields and filter rules. No filler. The only slight redundancy is repeating the profession list that the filter parameter also implies.

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 well by enumerating returned fields (slug, operator_id, display name, business name, city, profession, booking URL). Combined with strong annotations and full schema coverage, an agent can call it correctly; only pagination/limit and sort behavior are unaddressed.

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%, so the baseline would be 3. The description still adds value by specifying that filters match part of a value and are case-insensitive, which goes beyond the schema's examples and clarifies substring matching semantics. It does not state whether multiple filters AND together, a minor remaining gap.

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 ('Lists') and resource (Mane operators), enumerates the professions covered, and names the scope condition (opted in to be found through AI assistants). Returned fields and the opt-in scope let an agent distinguish this directory search from get_operator, which clearly retrieves a single record.

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: no filters means browse the whole opted-in directory, optional filters narrow by city/profession. However, no alternative is named — nothing tells the agent when to switch to get_operator, list_services, or list_availability instead of searching here. That leaves the sibling routing to inference.

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