Partelisto

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

Annotations already mark readOnlyHint=false and destructiveHint=false, but the description adds meaningful behavioral context: the operation requires separately granted write permission, should only be invoked after host confirmation, and will not send an email to the guest. This goes beyond the annotations and helps set expectations for side effects.

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 focused sentences with no filler: purpose first, then permission, then confirmation requirement, then the send_guest_checkin_link follow-up. Every sentence earns its place and the most important operational constraints are front-loaded.

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 7 parameters, no output schema, and sibling send_guest_checkin_link, the description plus a fully documented schema gives an agent everything needed to invoke the tool correctly. It covers permission, confirmation, side effects, and the relevant alternative/follow-up behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter thoroughly, including the templateId logic. The description adds only general context around property and dates rather than parameter-level detail. A baseline of 3 is appropriate because the schema is doing the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Creates a new booking (a check-in workflow) for one of the host's properties.' It clearly separates this from siblings like send_guest_checkin_link and list_bookings by defining what the tool itself accomplishes. The parenthetical clarifies the domain meaning of 'booking' rather than leaving it ambiguous.

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 explicit preconditions: write permission is required, and the host should confirm property and dates before calling. It also provides a when-not/what-next rule by stating it does not email the guest and directing the agent to send_guest_checkin_link if a link should go out. This is actionable guidance, not just context.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's job is lighter. It still adds meaningful behavioral context: the 50-booking scan window, the signed-in host scope, empty-list semantics, and the explicit 'No guest PII' guarantee. The exact return shape and ordering are not disclosed, but this is not critical for a read-only 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 two sentences with no filler. It front-loads the tool's action and outcome, then compactly lists the criteria and key behavioral facts (empty-list meaning, PII exclusion). Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with one optional parameter and no output schema, the description covers the input semantics, output selection criteria, empty-list behavior, and privacy boundary. The main unstated detail is the exact response structure, but the described behavior is sufficient for an agent to invoke it 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 single parameter arrivalWindowDays is fully documented in the schema with a default value and an explanation of the negative-gap meaning, giving a baseline of 3. The description itself does not add further parameter detail, but none is needed given the schema's complete coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it scans the signed-in host's recent bookings and returns only actionable items. It then enumerates the exact inclusion criteria (imminent/in-progress stays with no guest check-in, and failed SES.HOSPEDAJES submissions), which clearly distinguishes it from list_bookings and status-related siblings.

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 communicates when this tool is appropriate: it is for surfacing only items that need immediate action, and an empty list means nothing requires attention. However, it does not explicitly mention alternatives such as list_bookings for full booking history or get_guest_form_status for individual form status, so the exclusion guidance is implied rather than stated.

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 and idempotentHint, so the safety profile is covered. The description adds useful behavioral detail by stating the possible outcomes (None or Submitted) and explicitly clarifying that form content is not returned, which goes beyond the structured 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 that front-loads the primary result and includes a scope qualifier and an explicit exclusion ('No form content'). There is no filler or redundant restating of the tool name.

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 one-parameter, read-only status tool with rich annotations, the description is largely complete: it gives the possible values, the ownership constraint, and what is not included. It does not describe error behavior for non-owned bookings or invalid IDs, but that is a minor gap given the simplicity of 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?

Schema description coverage is 100% and the bookingId parameter is documented as 'The booking id.' The description adds that the booking must be one the host owns, but it does not provide additional format, constraints, or usage details, so the baseline of 3 is appropriate.

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 identifies the resource (guest check-in form status), the scope (booking the host owns), and the expected output values (None or Submitted). It lacks an explicit imperative verb like 'Get' or 'Returns', but the tool name plus description make the purpose unambiguous, and 'No form content' helps distinguish it from content-retrieval 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?

The description implies when to use the tool by scoping it to host-owned bookings and excluding form content. However, it does not explicitly mention alternatives or state when not to use it, such as when the caller is not the host or when form content is needed.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context by specifying that the data is scoped to the signed-in host and reflects the current month's usage, which implies time-dependent data. However, it does not describe response structure, potential absence of plan limits, or any edge behavior such as what happens when the host has no plan.

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 compact sentence that front-loads the subject (the signed-in host) and quickly enumerates the three key result categories: plan tier, trial status, and usage against plan limits. Every phrase earns its place; there is no repetition, filler, or schema duplication.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only summary tool, the description is adequately complete. It describes what the response covers and the scope ('signed-in host'), and the annotations cover the operational safety. The absence of an output schema is mitigated by the explicit enumeration of the result content, though a note on the format of usage limits would make it fully self-contained.

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 zero parameters, so parameter disambiguation is unnecessary. The description correctly focuses entirely on the output semantics, which is the appropriate baseline for a parameterless read-only tool. No parameter-related ambiguity exists.

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 identifies the tool's purpose: retrieving the signed-in host's plan tier, trial status, and current usage against plan limits. It names the specific resource (usage summary) and the data domains (properties, templates, bookings), which distinguishes it from sibling listing tools. It lacks an explicit verb like 'retrieves' or 'gets', but the tool name and content specification make the purpose 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 provides no guidance on when to use this tool versus alternatives such as list_bookings or list_properties. It implies it is for account-level usage/limit checking, but does not state explicit conditions, exclusions, or comparison with sibling tools. An agent would need to infer from the tool name that this is for plan usage rather than operational data.

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?

Beyond the readOnlyHint and idempotentHint annotations, the description adds valuable behavioral context: results are newest first, paged, and explicitly never include guest email, phone, or documents. This privacy guarantee is important for an agent deciding whether this tool fits a request.

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 cover scope, ordering, paging, return fields, and exclusions. Every phrase carries information, and the core action is front-loaded.

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 a fully documented schema and safety annotations, the description is complete. It explains what is returned, what is never returned, and the paging behavior, so an agent has everything needed to invoke it 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 input schema already fully documents skip and take, including defaults and max value, so the baseline is 3. The description only adds that results are paged, which reinforces the schema without adding new parameter-level detail.

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 lists the signed-in host's bookings, with explicit ordering and paging. It distinguishes itself from sibling resources like list_properties and send_guest_checkin_link by naming the exact resource and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes clear this is for retrieving the signed-in host's bookings and that results are paginated. It does not explicitly state when to avoid this tool or prefer a sibling, but the resource and scope are specific enough for an agent to select it correctly.

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 and idempotentHint, so the safety profile is covered. The description adds meaningful context about scope (signed-in host) and data boundaries, without contradicting annotations. Minor gaps like ordering or pagination are not critical for this simple read-only list.

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 states the operation, scope, and returned fields without wasted words. The 'No guest data' exclusion is concise and valuable.

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 listing tool with one optional parameter, the description is complete: it names the resource, scope, included fields, and exclusion. The output schema is absent, but the description enumerates the return fields sufficiently, and annotations cover behavioral safety.

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 fully documents the single optional includeArchived parameter with its default and meaning, so the description does not need to add parameter details. The description adds no extra parameter-level semantics, but the high schema coverage keeps this at baseline.

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 ('Lists') and resource ('signed-in host's properties') and enumerates the returned fields. It also draws a clear boundary with 'No guest data,' distinguishing it from guest-related sibling 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?

The description clearly establishes when to use the tool: to list the signed-in host's properties. The explicit 'No guest data' note provides a useful when-not signal, though it does not name alternative sibling tools for guest-specific operations.

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 establish read-only and idempotent behavior. The description adds non-obvious behavioral context: bookings without a submission are omitted, and the response includes attempts, last error, and official reference once accepted. This goes beyond what the annotations and schema provide.

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 with no filler. The description front-loads the domain and purpose, then adds the important omission caveat. Every sentence contributes useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter, read-only tool with no output schema, the description covers purpose, scope, returned fields, and the omission behavior. It does not specify response formatting or possible status values, but an agent has enough information to select and invoke the tool 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 single parameter is fully documented in the schema ('Booking ids to check, up to 50'), so the baseline applies. The description reinforces that the ids refer to host-owned bookings, but adds no additional syntax or constraints beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (SES.HOSPEDAJES police-registration submissions) and the action (checking status for host-owned bookings), and lists the returned fields. It is clearly distinct from list_bookings, but it does not explicitly differentiate from the sibling get_guest_form_status, 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?

The use case is implied—check SES submission status for a set of bookings the host owns—and the host-ownership scope is stated. However, there is no explicit when-to-use guidance, no mention of alternatives, and no condition distinguishing it from get_guest_form_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?

Beyond the annotations, the description discloses concrete side effects: 'it emails the guest and, on resend, invalidates the guest's previous link.' It also adds the write-permission and host-confirmation requirements, giving the agent a strong behavioral model.

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 concise sentences front-load the core action and side effect, then add permission and confirmation guidance. Each sentence earns its place with 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 mutating tool with no output schema, the description covers the essential pre-invocation context: side effect, link invalidation, required permission, and the need for host confirmation. The schema handles parameter details, and siblings are plainly different read-only tools.

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 100% coverage with clear descriptions for bookingId, email, and guestName. The description does not add parameter-specific meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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 the specific action: 'Sends (or resends) the guest check-in link by email for a booking the host owns.' This clearly identifies a verb and resource and is easy to distinguish from the sibling get/list 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?

Provides clear usage context: the tool requires write permission and the agent should 'Ask the host to confirm before calling this.' It does not explicitly name alternative tools or say when not to use it, so it stops short of a 5.

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