slotrobin

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), so the description only needs to add context. It does add real value: the three outcome states (confirmed, pending with the business confirming, failed) and the fact that a reference is returned. It omits any auth or rate-limit behavior, keeping it short of 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?

Three sentences, no waste, and the core purpose is front-loaded before the precondition and the return-value note. Every sentence adds information an agent needs.

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, describing the confirmed/pending/failed returns and the reference is exactly the right compensation, and the confirmation gate is covered. It falls short only on the seven undocumented input parameters, which an agent still has to infer.

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 9 parameters, so the description carries the full burden — yet it only clarifies customer_confirmed (and implicitly start, by tying it to check_availability). business_id, service_id, customer_name, notes, agent_name, customer_email and customer_phone are left entirely undocumented in both schema and description.

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 ('Book a time') and ties the resource to the sibling check_availability, so an agent can distinguish it from cancel_booking, request_quote, and the rest without opening a schema. The dependency on a prior availability result makes the scope 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?

Gives an explicit precondition: use only after the customer has said yes to this exact business, service and time, and set customer_confirmed=true to signal it. That is strong when-to-use guidance, though it never states when *not* to use it or names the alternative path (e.g. request_quote) for the unconfirmed case.

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 destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely non-structured context: the customer-confirmation gate that must precede the call, and the ordering requirement that a reschedule must complete before cancelling. It does not state reversibility or what happens to the slot after cancellation, which keeps it short of 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?

Three short sentences, front-loaded with the core action, then the gating condition, then the alternative workflow. Every sentence carries distinct operational information with no repetition of the title or schema.

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 does not describe the result of a successful or failed cancellation, but annotations already carry the destructive/idempotent semantics and the description covers the decision procedure and the critical gating flag. Adequate for an agent to invoke correctly, with only the return behavior 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 description coverage is 0% for 4 parameters, so the description must compensate. It does explain customer_contact ('the email or phone used for the booking') and customer_confirmed ('set true to say so'), but leaves reference and business_id entirely undocumented in both schema and prose.

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 ('Cancel a booking made earlier'), immediately distinguishable from siblings like book_appointment and check_availability. The follow-up sentences further pin down scope by naming the reschedule workflow and the sibling tools involved in it.

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 after the customer has clearly said they want to cancel'), tells the agent exactly how to signal it (set customer_confirmed=true), and routes the alternative scenario (reschedule) through a concrete ordered sequence of sibling tools. Nothing 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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real behavioral constraints beyond them: the 14-day maximum window and the fact that returned times are offers rather than reservations. It does not disclose result shape or rate limits, so it falls short of 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?

Three short sentences, zero filler, with the format constraint and the example placed immediately after the purpose. The opening fragment is slightly telegraphic but not wasteful.

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, so the description should say more about what comes back — a list of slots, whether times are returned in the requested offset, and how business_id and service_id relate. The 14-day and offers-not-holds details are genuinely useful, but the return-value gap leaves it only partially 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 description coverage is 0% with four required parameters, so the description must compensate. It documents start and end thoroughly (ISO 8601 with UTC offset, concrete example, 14-day span), but leaves business_id and service_id entirely unexplained.

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 outcome ('Open times for a service'), which an agent can distinguish from book_appointment and list_services in the sibling set. It is a noun phrase rather than a verb+resource construction, but the intent 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?

Usage is only implied: 'Times are offers, not holds' hints that a follow-up booking (book_appointment) is required, but no alternative tool is named and no explicit when/when-not condition is given.

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, openWorldHint, and destructiveHint=false, so the safety profile needs no disclosure. The description does add value by enumerating the statuses it reports (confirmed, declined, replied), which is behavioral context beyond the annotations, but it says nothing about error cases, rate limits, or what an unmatched reference yields.

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 compact sentences with no filler, and the purpose question is front-loaded ahead of the parameter hints. The question phrasing is slightly indirect but does not waste 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 simple read-only lookup whose annotations already cover safety, the description supplies the purpose question and clarifies two of the three inputs. The absence of any mention of business_id and of return shape (no output schema exists) are the only meaningful gaps.

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 explains two of three parameters – reference (the value returned by request_quote/book_appointment) and customer_contact (email or phone) – but leaves business_id entirely undefined in both schema and description.

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 frames the tool as a status query ('Has the business confirmed, declined or replied?') and ties it to a previously-submitted request, which combined with the name makes the purpose clear. It names the sibling tools (request_quote, book_appointment) whose reference is the input, giving some differentiation, though it never states the resource being checked 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?

It implies usage context by specifying that the reference comes from request_quote or book_appointment, so the agent knows this is a follow-up call. There is no stated when-not-to-use, no exclusions, and no reference to alternatives among the remaining siblings.

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, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered. The description adds nothing behavioral beyond that — no mention of result limits, pagination, ranking, or breadth of the directory search.

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 lines, purpose front-loaded, then parameter examples in name: meaning form. No filler.

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 search with no output schema, the description covers purpose and parameter meaning adequately, but omits result-shape expectations (how many businesses, what fields) and matching behavior, leaving the agent to infer them from the response.

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% (only titles and empty defaults), so the description must compensate — and it does, giving a concrete example for each of the three parameters (query='plumber', category='plumbing', locality='Petawawa'). It doesn't clarify matching semantics (substring vs exact, AND/OR combination), so it falls just short of 5.

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 (Search) and resource (directory of bookable service businesses), which clearly separates it from get_business (single lookup) and list_services (services within a business). It stops short of explicitly naming a sibling, but the scope 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?

'All filters optional' tells the agent every call is valid with zero arguments, which is useful implied usage, but there is no guidance on when to prefer this discovery tool over get_business or list_services once a business is known.

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 openWorldHint, so safety and mutability are covered structurally. The description adds the content scope but says nothing about auth requirements, rate limits, or how the entity id is obtained; with rich annotations this is an adequate but not additive disclosure.

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 clauses, zero filler, with the resource and its contents front-loaded. Every phrase contributes meaning.

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 an output schema present, the return values need no further explanation, and annotations cover the safety profile. The remaining gap is procedural: an agent still doesn't know where to obtain business_id, which matters for a single-parameter tool with no schema documentation.

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 0% for the single business_id parameter and the description never explains it — not its format, nor that it likely comes from find_businesses. The phrase "a business's booking page" only implies an id is needed, which the schema already enforces.

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 (read a business's booking page) and enumerates what comes back: services with ids, prices, hours rules, and booking instructions. It is clearly distinct from find_businesses, though it does not explicitly contrast with list_services, which also surfaces services.

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?

"Read this first" gives a clear ordering directive that tells the agent to call this before book_appointment/check_availability. No when-not guidance or named alternative is given, but the sequencing context is 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds useful domain context by noting services are 'bookable or quote only', but says nothing about pagination, result limits, or empty-result behavior. With annotations carrying the safety burden, a 3 is appropriate.

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 front-loaded sentence with no filler; the parenthetical field list earns its place by previewing the return shape. Slightly dense but appropriately sized for a simple list 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?

With no output schema, the description helpfully enumerates the returned fields (id, name, duration, price basis, bookable/quote-only), which is exactly what the agent needs. For a one-parameter read tool with full annotation coverage, this is nearly complete; only the business_id format is left 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?

There is one required parameter, business_id, with 0% schema description coverage, so the schema contributes nothing. The description implies the business identifier by saying 'a business's services' but never states the expected format or where to obtain it, so it only partially compensates.

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 (List) and resource (a business's services) and even enumerates the returned fields, so the agent knows exactly what it retrieves. It does not explicitly differentiate itself from siblings such as get_business, which could also surface service data, so it stops 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?

There is no when-to-use guidance, no prerequisites, and no mention of an alternative tool. An agent must infer that this is the lookup to call before booking or quoting, which is not stated anywhere.

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=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds real workflow context beyond that: a mandatory human-confirmation precondition and the fact that the business needs a contact channel to reply. It omits what happens after submission (e.g., status tracking via check_request_status).

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 with zero filler, front-loaded with the action and immediately followed by the precondition and contact requirement.

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 non-idempotent, open-world mutation with no output schema and 10 undocumented parameters, the description covers the critical precondition and contact requirement but leaves most input fields unexplained. Adequate to call correctly in the common path, incomplete for the full parameter surface.

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 10 parameters, so the description must carry the burden. It explains only customer_confirmed and the email-or-phone requirement (an important constraint, since both default to empty and neither is required in the schema), leaving business_id, description, customer_name, service_id, agent_name, address_or_area, and preferred_times 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?

States a specific verb+resource ('Send a quote request to the business'), which is clearly distinct from book_appointment or check_availability. It does not explicitly name a sibling to route against, so it stops 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?

Gives an explicit gating condition: only send after the customer has confirmed the details, and set customer_confirmed=true to record that. It does not name alternatives (e.g., book_appointment vs. this request), but the when-to-use rule is clear and actionable.

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