TaskMan of London

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

With no annotations provided, the description carries the full burden of disclosure. It does not mention read-only behavior, permission requirements, return format, or side effects, leaving the agent without insight into the tool's safety or operational characteristics.

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, concise sentence with no filler. It is front-loaded with the trigger condition, making it easy to scan, though it may be too brief for the tool's complexity.

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?

The tool has 4 parameters, no output schema, and no annotations, yet the description only addresses when to use it. It lacks information about inputs, outputs, and any behavioral nuances, leaving significant gaps for the agent.

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%, and the description provides no information about parameters. It does not explain how service_type, postcode, preferred_date, or time_preference are used, failing to compensate for the schema's lack of descriptive comments.

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 trigger condition ('Use when...') rather than a direct statement of functionality. It implies the tool checks booking likelihood but does not clearly state what it checks (service availability, timing, etc.), and it does not differentiate from sibling tools like check_service_area or get_customer_availability.

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 provides a clear usage context: user asks about dates, timing, or booking likelihood. However, it lacks explicit exclusions or references to alternative tools, which would improve the guidance.

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 the full burden of behavioral disclosure. It only mentions the trigger condition, not what the tool actually does (e.g., return a boolean, coverage rules, or any side effects). The agent is left guessing about the tool's behavior beyond its name.

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 that conveys the core usage context without any filler. It is appropriately sized for the tool's simplicity.

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 tool with no annotations and no output schema, the description is incomplete. It fails to mention return value, the role of 'service_type', or any limitations beyond the London postcode hint. This leaves significant gaps for an agent to operate correctly.

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 0% description coverage, so the description must compensate. It adds meaning to 'postcode' by specifying London, but it completely ignores 'service_type', leaving the agent to infer its purpose. The description adds partial value but not sufficient for full parameter understanding.

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 indicates the tool checks whether TaskMan covers a given London postcode, which is a specific operation on a specific resource. It frames it as 'Use when...' rather than a direct statement, but the intent is unambiguous and distinct from sibling tools like check_availability or find_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?

The description explicitly states when to use this tool: when the user provides a London postcode or asks about area coverage. It does not mention alternatives or exclusions, but the context is clear enough for an agent to select it appropriately.

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 must disclose side effects and semantics. It only hints at creating a 'real' booking request but fails to explain actual behavior, such as whether it creates a record, requires additional steps, or triggers notifications.

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 concise sentence, but it is under-specified for a complex tool. It lacks structure and critical detail, making it an inefficacious use of brevity.

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?

Given 12 parameters, 6 required, no annotations, and no output schema, the description is wholly inadequate. It tells when to use but nothing about input semantics, expected outcomes, or constraints.

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 12 properties with 0% description coverage, and the tool description provides no parameter details. It does not explain required fields like consent_to_contact or any optional fields, leaving the agent to infer solely from property names.

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 indicates the tool is for submitting details for a real TaskMan of London booking request. It clearly implies an action (submit details) but lacks an explicit verb like 'create' and does not differentiate from the sibling 'create_customer_booking'.

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?

Explicitly states 'Use when the user is ready', providing a clear trigger condition. However, it does not mention when not to use the tool or name alternative tools for similar purposes.

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 provided, the description carries the full transparency burden. It mentions preconditions and scope but does not disclose side effects, error conditions, return values, or how the session_token and payment_session_id are used. This is minimal for a create operation.

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, tightly-worded sentence with no filler. Every phrase ('after verification', 'confirmed paid payment session', 'scoped to the verified customer') conveys essential context.

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?

Given the tool has 11 parameters, no annotations, and no output schema, a one-sentence description is insufficient. It omits details about required parameters, optional fields, idempotency behavior, and the response format, leaving the agent with significant 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%. The description does not explain any of the 11 parameters, such as the relationship between session_token and the customer, or the role of idempotency_key. It adds no semantic value beyond what the schema already provides.

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 action ('create a booking') and the scope ('scoped to the verified customer'). It distinguishes itself from sibling tools like create_booking_request by requiring a confirmed paid payment session as a precondition.

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 explicitly states when to use this tool: 'after verification, detail collection, and confirmed paid payment session'. This implies the necessary preceding steps but does not name alternative tools or explicitly state when not to use it.

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?

There are no annotations, so the description alone must disclose behavioral traits. It only states an intent ('identifying which service fits') without explaining what happens when invoked—whether it returns a list of suggested services, whether it reads or writes data, or any side effects. This is a significant gap for a tool with no other behavioral metadata.

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 sentence with no filler, front-loaded with the usage trigger 'Use when...'. It is concise and structured appropriately for the limited content it provides, though its brevity contributes to the lack of behavioral depth.

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 and no annotations, the description should cover what the tool returns and how it behaves. It only gives a usage scenario, leaving the agent without enough context to know what to expect from the tool or how to interpret its result. The description is incomplete for a tool with this complexity.

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 input schema has three parameters (area, query, urgency) with zero descriptions, and the tool description mentions none of them. Schema coverage is 0%, so the description should compensate by explaining how these parameters relate to the vague home-service use case, but it does not. Even the parameter names are left open to interpretation.

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 a specific action: helping identify which TaskMan of London service fits a job. This distinguishes it from sibling tools like list_service_types (which would just list types) and match_providers (which matches providers). The added context 'especially for vague home-service requests' further sharpens the 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?

The description explicitly starts with 'Use when...' and gives a concrete scenario: vague home-service requests in London. This provides clear context for when the tool is appropriate. However, it does not mention when not to use it or name alternative tools, stopping short of a full usage guideline.

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 must carry the behavioral transparency burden. It does disclose the possible statuses the tool checks for, which provides some behavioral context. However, it does not explicitly state that this is a read-only operation, describe the response structure, or mention any permissions or error conditions.

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 sentence, front-loaded with the action ('Use to check'), and contains no redundant information. Every word contributes to the purpose.

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?

The description covers the primary purpose and timing, and lists possible statuses, but it omits details about return values, parameter handling, and error behavior. Since there is no output schema, more detail on the response would improve completeness, though the tool's simplicity keeps this from being a serious 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?

The schema has 0% description coverage, and the description does not explain the two required parameters (session_token and payment_session_id). The parameter names give a general hint, but the description adds no additional meaning, forcing the agent to rely on the names alone.

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 uses a specific verb 'check' with a specific resource 'booking payment session' and enumerates all possible statuses (pending, paid, failed, canceled, expired). This clearly distinguishes it from sibling tool get_booking_status, which is about general booking status rather than payment session status.

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 explicitly states when to use the tool: 'before attempting booking creation'. This provides clear usage context. However, it does not mention alternatives or when-not-to-use, so it does not fully meet the highest bar.

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 the full burden of behavioral disclosure. It only implies a read-only operation via the name 'get', but doesn't explicitly state that it's read-only, what the response contains, or how errors are handled. This is minimal transparency for a tool with no annotation support.

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 sentence with no wasted words, making it concise and easy to parse. However, its brevity comes at the cost of crucial information, so it's efficient but under-specified for a tool with multiple parameters.

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?

Given there is no output schema and no annotations, the description is too sparse to provide a complete picture. It doesn't explain return values, parameter usage, or edge cases, making it hard for an agent to invoke correctly without external knowledge.

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%, and the description adds no explanation of the three parameters. The required booking_request_id is vaguely implied by 'has a TaskMan booking request', but the optional email and phone parameters are completely undocumented, leaving the agent without guidance on their purpose.

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 implies the tool retrieves booking status by stating 'wants an update', but it lacks an explicit verb+resource formulation such as 'retrieves the current status of a booking'. It also doesn't distinguish from the sibling get_booking_payment_status, leaving potential ambiguity.

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 clearly states when to use the tool: when the user already has a TaskMan booking request and wants an update. It provides an explicit precondition and intent, which is strong guidance, though it doesn't mention alternatives or when not to use.

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 must disclose behavioral traits. It only says 'check availability', which largely restates the tool name. It does not mention whether the operation is read-only, requires specific permissions, what happens if the customer is not verified, or what the output looks like. It adds nothing beyond the name's implication.

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 sentence, concise and front-loaded with the key condition 'after verification'. It is not bloated, but it is slightly redundant with the tool name (e.g., 'check availability' vs 'get_customer_availability'). It earns its place but could provide more detail without becoming overly long.

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 5 parameters, no output schema, and no annotations, the description is insufficient. It does not explain return values, required parameters, or behavioral nuances. The description is too high-level to fully guide an agent in invoking this tool correctly, especially given the sibling tools and schema complexity.

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 compensate. It makes no mention of `service_type`, `preferred_date`, `time_preference`, or `session_token`, and only indirectly implies `address_id` via 'selected saved address'. The description provides no parameter-level meaning, leaving the schema to stand alone.

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 uses a specific verb ('check availability') and clearly scopes to a 'verified customer' at a 'selected saved address', which distinguishes it from siblings like `check_availability` and `check_service_area`. It clearly states the target entity and condition.

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 explicitly states 'Use after verification', which is a clear precondition for when to invoke this tool. It does not explicitly list alternatives or exclusions, but the context implies it is part of a verified-customer booking flow with saved addresses. This is clear but not fully exhaustive.

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 provided, the description carries full burden to disclose behavioral traits. It uses 'load' to imply a read-only operation but does not explicitly state that it causes no side effects, what data is returned, or whether it requires any special permissions beyond the session token. The description lacks critical behavioral 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?

The description is a single, tightly worded sentence (12 words) that front-loads the main action and context. Every word adds value, with no redundant phrasing or irrelevant details.

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?

The tool has no annotations, no output schema, and a sparse description. For an agent to use it correctly, it needs to know what 'scoped customer profile details' includes, the return format, and how the session_token is used. The description is too brief to provide sufficient contextual completeness for a tool in a complex CRM workflow.

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 one required parameter, session_token, with no description. The tool description does not mention this parameter at all, even though it is essential for invocation. With schema description coverage at 0%, the description fails to compensate, leaving the agent unsure about the parameter's role.

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 tool loads customer profile details from CRM for booking, using the verb 'load' and specifying the resource ('scoped customer profile details') and context ('for booking'). This distinguishes it from sibling tools like get_customer_availability or list_customer_addresses, though the term 'scoped' is somewhat vague.

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 phrase 'Use after verification' provides an explicit precondition and clear usage context. It implies the tool should not be used before verification, but does not explicitly name alternatives or exclusions, so it falls just 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?

With no annotations provided, the description carries the full burden for behavioral disclosure, yet it offers none. It does not mention what the tool returns, whether it depends on service area or provider availability, any side effects, or required inputs beyond the schema.

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 concise sentence that immediately conveys the intended use case. It is front-loaded with actionable trigger phrases and contains no filler or 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?

Given the tool's complexity (9 parameters, no annotations, no output schema), the description is severely incomplete. It does not explain what a quote estimate looks like, how it is calculated, or what the agent should expect after invocation. The description only addresses when to use, not how to invoke or interpret results.

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%, and the tool has 9 parameters including required ones like service_type and task_summary. The description provides no information about how parameters influence the estimate, such as item_count, postcode, or preferred_date. It completely fails to compensate for the schema's lack of descriptions.

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 the tool is for user inquiries about 'likely cost, ballpark pricing, or whether a task needs a custom quote,' which implies it provides quote estimates. However, it is phrased as a usage trigger rather than a clear verb+resource statement, so the actual function (e.g., 'retrieves a quote estimate') is vague.

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 explicitly says 'Use when the user asks about likely cost, ballpark pricing, or whether a task needs a custom quote,' providing clear triggering conditions. It does not mention alternatives or when-not-to-use, but the context is specific enough to guide selection.

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 disclosure burden. It reveals that the session must be verified (an authentication requirement) and that the operation lists saved addresses (implying a non-destructive read). It does not detail error responses, pagination behavior, or what exactly constitutes a 'verified' session, but the core safety profile is adequately conveyed.

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 that efficiently combines the precondition ('Use after verification') and the core action ('list saved addresses linked to the verified customer'). There is no redundant or unnecessary wording, making it highly concise and well-structured.

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?

The tool is simple: one required parameter, no output schema, and no nested objects. The description covers the essential context: when to use (after verification), what it does (lists saved addresses), and the scope (linked to the verified customer). It omits details like pagination or response format, but these are likely unnecessary for a basic read operation, so the description is sufficiently 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%, so the description must compensate. It connects the session_token (the only parameter) to the 'verified customer' context, indicating the token must come from a successful verification. While it does not mention the parameter by name or its format, the self-explanatory schema name and the added verification context provide sufficient semantic guidance for a single-parameter tool.

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 uses the verb 'list' with the resource 'saved addresses linked to the verified customer.' It also specifies the prerequisite 'after verification,' which makes the tool's purpose distinct from sibling tools like get_customer_profile or start_customer_verification. No sibling tool covers listing customer addresses, so 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?

The description explicitly states 'Use after verification,' providing a clear when-to-use condition tied to the verification workflow. However, it does not mention alternatives or when not to use the tool (e.g., before verification or for other address-related queries), so it stops short of a full 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds workflow constraints (after verification, before booking) but does not explicitly state side effects or return format. The verb 'list' implies read-only, but more explicit behavioral context would strengthen this dimension.

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 sentence, front-loaded with the usage condition, and contains no redundant information. Every word adds value.

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 list tool with one parameter and no output schema, the description covers purpose and workflow adequately. It doesn't detail the response shape, but the low complexity makes this acceptable.

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 the only parameter, session_token. The description does not directly explain the parameter, instead only indirectly referencing verification. The parameter name is self-explanatory, but the description fails to compensate for the schema gap by linking the token to the verification step.

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 uses the specific verb 'show' and identifies the resource 'supported service types', making the tool's purpose unmistakable. It also distinguishes from siblings like find_services and check_availability by indicating it's a pre-booking enumeration of types.

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 explicitly states when to use: 'Use after verification' and 'before collecting booking details', giving a clear workflow position. It doesn't name alternative tools, but the context is sufficient for a simple listing tool.

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 provided, the description carries the full burden. It discloses the sorted candidate return and the assignment rule (first can_assign=true), which is valuable. However, it does not address edge cases like no matching provider, error behavior, or whether any state is mutated, leaving notable gaps.

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 two sentences, front-loaded with usage context, and contains no filler. Every word adds value, making it highly efficient.

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?

Given the tool has 5 parameters, no output schema, and no annotations, the description is too brief. It covers the core return behavior but omits parameter semantics, error handling, prerequisites, and potential side effects, making it incomplete for safe and correct invocation.

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%, and the description does not explain any of the five parameters (urgency, location_id, service_type, area_postcode, preferred_date). The schema provides enums/types but no semantic guidance, and the description adds no parameter meaning, so the agent must guess how to set these fields.

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 indicates the tool produces a provider-matching result for assignment, and specifies the return format (ordered_candidates array with first can_assign=true as assignee). This distinguishes it from siblings like find_services or check_availability, though it doesn't explicitly use the verb 'match' beyond the tool name.

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 opening phrase 'Use when an agent needs a single deterministic provider-matching result for assignment' provides clear context for when to use the tool. It implies exclusivity (single deterministic result) but does not explicitly name alternatives or state when not to use it.

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 but only states a Stripe session is created; it fails to disclose side effects, auth, or reversibility of payment.

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 sentence, no filler, front-loaded with usage context.

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?

Given 7 parameters, no output schema, and no annotations, a single sentence is insufficient to guide an agent on parameter values, return shape, and failure states.

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% and description mentions no parameters, leaving all 7 fields' semantics to the schema alone.

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 it creates a Stripe checkout payment session, with clear sequence ('after collecting booking details', 'before final booking submission'), distinguishing it from booking creation/status tools.

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?

Explicitly instructs to use after collecting booking details, implying placement in workflow, but does not name exclusions or alternatives like get_booking_payment_status.

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 must disclose behavior. It only mentions the verification methods (OTP/magic link) and the timing, but it does not state what side effects occur (e.g., sending a code), whether it is a read or write operation, or what happens after the call. This is insufficient for the agent to understand the tool's impact.

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 sentence that is front-loaded with the usage condition. It is concise and avoids extraneous detail, but it may be too lean given the complexity of the 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?

Given the tool has three parameters, no annotations, and no output schema, the description is far from complete. It fails to explain the overall verification flow, the relationship to the verify OTP/magic link tools, error conditions, or what the response contains. The agent would lack critical context for invoking and handling the 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?

The schema has three parameters with 0% description coverage. The description mentions OTP and magic link, which partially explains the method_preference enum, but it does not clarify the identifier parameter or the channel_preference options. Agents would need to infer the purpose of these parameters from context.

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 clear usage context: verifying an existing customer's identity via OTP or magic link before booking. The verb 'start' in the tool name clarifies it initiates the process, but the description does not explicitly distinguish it from the sibling verify_customer_otp and verify_magic_link_token tools, which are likely subsequent steps.

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 explicitly states when to use the tool: when an existing customer needs identity verification before assistant-led booking. It provides a clear trigger context but does not mention exclusions or alternative tools, such as when to use the verification completion 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?

No annotations are provided, so the description carries the full burden. It mentions the purpose (short-lived session) but does not disclose what the tool actually does on invocation, such as side effects, return values, error conditions, or how the session is used afterward. This is a significant gap for a mutation-like 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?

The description is a single sentence that is front-loaded with the use case and purpose. It contains no wasted words and earns its place by conveying both when and why to use the 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?

Given the low complexity (1 parameter, no output schema, no annotations), the description provides some context about the flow and purpose but leaves critical gaps: what the identifier is, what the session entails, and how it integrates with sibling tools. It is minimally adequate but not 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?

The schema has one parameter 'identifier' with no description (0% coverage). The description mentions 'caller number' but does not explicitly define 'identifier' as that caller number, leaving ambiguity. It fails to compensate for the lack of schema descriptions.

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 tool's purpose: to start a short-lived booking session in trusted telephony flows when the caller number is already verified by the channel provider. It uses a specific verb ('start') and resource ('trusted phone session'), and differentiates from OTP-based verification by explicitly noting 'without OTP'.

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 provides clear context for when to use the tool: 'trusted telephony flows' with a pre-verified caller number and a need for a session without OTP. It implies when not to use it (when OTP is required or caller not verified), but does not explicitly name alternative 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?

No annotations are provided, so the description carries the full burden. It discloses a precondition ('verified customer') but fails to explain side effects, idempotency, or return behavior. This is insufficient for a mutation 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?

A single sentence that is front-loaded and contains no filler. Every word contributes to describing the tool's purpose.

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?

The description gives the essential purpose and a key precondition, but lacks details on behavior, errors, and return values. For a simple tagging tool, it is minimally adequate.

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%; the description doesn't mention the required 'session_token' parameter or explain 'tags' beyond the bare concept. It doesn't compensate for the schema's lack of descriptions.

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 uses the specific verb 'add' with a clear resource ('CRM tags') and context ('verified customer for booking workflow tracking'). It clearly distinguishes this from sibling tools like update_contact_note or verification tools.

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?

States a direct usage instruction ('Use to...') and provides context (booking workflow tracking), making it clear when this tool is appropriate. However, it doesn't mention exclusions or alternatives for when not to use it.

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?

The description conveys the core behavior (append, internal note, verified customer) and implies a precondition (verification). However, with no annotations provided, it does not disclose whether the operation is destructive/reversible, what the response indicates, or any permission requirements. The word 'verified' is a useful hint but not fully explained.

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 that conveys the purpose without redundancy. Every word earns its place, and there is 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 mutation tool with no annotations, no output schema, and incomplete parameter documentation, the description falls short. It does not cover return behavior, preconditions beyond 'verified', session token requirements, or error conditions, leaving an agent to infer too much.

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%, and the description only indirectly covers the 'note' parameter by mentioning 'internal CRM note'. It does not mention or explain 'session_token' at all, leaving its purpose and requirements 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 ('append') and resource ('internal CRM note') with context ('for the verified customer during or after booking'). It clearly distinguishes from sibling tools, none of which target note management.

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 provides clear usage context (append note during or after booking for a verified customer) but does not explicitly mention when not to use it or name alternatives. Since no sibling tool handles internal notes, the lack of alternatives is acceptable.

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 provided, the description carries the burden of behavioral disclosure. It does reveal a key side effect—opening a 'short-lived booking session'—but it omits other relevant behaviors such as whether the OTP is consumed on unsuccessful attempts, failure scenarios, or session duration specifics. It adds some value but lacks depth.

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 sentence, front-loaded with the usage trigger ('Use after sending an OTP challenge'), and contains no redundant or verbose language. Every word adds value, making it highly concise and well-structured.

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?

The tool has only two parameters and no output schema or annotations. The description covers the purpose, timing, and a key outcome, but it does not explain what the tool returns or how errors are handled. For a simple verification action, this is minimally viable but leaves gaps that could be filled with more detail.

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 compensate. It indirectly maps 'OTP challenge' to challenge_id and 'one-time passcode' to otp_code, providing domain context that the schema lacks. However, it does not explicitly detail parameter meaning or provide examples, so it only partially compensates for the coverage 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?

The description uses a specific verb 'verify' and identifies the resource as 'one-time passcode', while also mentioning the outcome of opening a 'short-lived booking session'. This clearly distinguishes it from sibling tools like verify_magic_link_token, which verifies a different mechanism.

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 phrase 'Use after sending an OTP challenge' provides explicit context on when to invoke this tool, but it does not mention alternative tools or explicitly state when not to use it. This is clear context without exclusions, so it earns a 4.

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 provided, the description carries the full burden of behavioral disclosure. It does not state whether the token is consumed/expired, what happens on success or failure, or any side effects. The single phrase 'for verification' is insufficient to understand the tool's runtime behavior.

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 short sentence, which is efficient, but it packs little substance—just a usage trigger and a vague reference to verification. It is not bloated, yet it sacrifices necessary detail for brevity, making it minimal rather than optimally concise.

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?

Given the tool has one parameter, no output schema, and no annotations, the description should explain what the verification returns, error behavior, or lifecycle—none of which it does. The description is too sparse to be considered a complete guide for an AI agent invoking this 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?

The schema has 0% description coverage for the token parameter. The description only references 'the token' generically, without explaining what a valid token looks like, how it is generated, or any constraints beyond the schema's min/max length. This does not compensate for the lack of schema documentation.

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 indicates the tool verifies a magic link token, using the phrase 'for verification' and contextualizing 'when the customer clicks a magic link.' It distinguishes from siblings like verify_customer_otp by specifying the magic link context, though the function is not explicitly stated as 'verifies' but 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?

The description gives an explicit when-to-use trigger: 'Use when the customer clicks a magic link and provides the token for verification.' This is clear context for usage, and while it doesn't explicitly mention alternatives, the magic link framing differentiates it from OTP-related siblings.

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