The Driscoll Public AI

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

Adds significant behavioral context beyond annotations: ranges are never merged, platform occupancy rules apply, and nightly amounts/subtotal are returned only when every requested night has a current amount. It also discloses it cannot hold or confirm, which is extra context beyond the read-only annotation.

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 compact paragraph of four sentences, front-loaded with the main purpose. Every sentence adds meaningful information, with no redundancy or fluff.

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 main behavior and output for the success case, including nightly amounts and subtotal. However, it does not explicitly state what happens if not all nights have current amounts, which is a minor gap given the absence of an output schema.

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 descriptions cover 50% of parameters. The description adds meaning for platform (applies occupancy rule) and dates (single range requirement), but does not explain the semantics of adults, infants, or children beyond schema. Thus it partially compensates for missing parameter info.

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 specifically states it 'Interpret the current public availability feed for one proposed stay,' clearly identifying the tool's action and scope. It also explicitly distinguishes itself from booking tools by noting it cannot confirm reservations or final prices.

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: for an indicative check of a single stay window that must fit within one range. It implies boundaries by stating what it cannot do (hold dates, confirm), but does not explicitly name alternative tools or exclusions.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the tool's safe, read-only nature is covered. The description adds useful context beyond annotations, such as the platform-specific behavior and the fact that the property website does not take direct bookings or payments, which helps set expectations for the agent.

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 the primary function, and includes a relevant non-obvious fact about the property website. There is no wasted wording or redundancy with schema/annotations.

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

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

For a simple one-parameter, read-only tool, the description is complete. It specifies what is returned (booking links and occupancy rule) and gives a critical constraint (no direct bookings/payments). No output schema exists, but the return content is adequately summarized, and sibling differentiation is sufficient.

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 provides 100% coverage with a clear parameter description, so the description adds little beyond the schema. The 'platform-specific occupancy rule' mention relates to the platform parameter but doesn't elaborate on enum values; schema already explains them sufficiently.

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 'Return' with a clear resource: 'The Driscoll's authorised booking links and platform-specific occupancy rule.' It also adds a key differentiator from siblings by noting that 'The property website does not take direct bookings or payments,' which clarifies its unique role among booking-related 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: whenever booking options or platform occupancy rules are needed. It provides clear context by stating the property website doesn't handle bookings directly, but it does not explicitly name alternatives or exclusions relative to sibling tools like check_stay_availability.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral specificity by stating it never resets, reconfigures, disassembles, or controls equipment, which reassures an agent about the non-invasive nature of the 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?

Two tightly written sentences accomplish a lot: they define the purpose, set safety expectations, and define the input type. There is no filler, and the most important information 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 one-parameter, read-only tool, the description explains what it does, what it does not do, and how the input should be interpreted. It does not describe the output format, but 'closest curated sections' and the absence of an output schema make the return concept reasonably clear.

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

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

Schema coverage is 100%, so the parameter is already documented. The description adds meaning by clarifying that the input is search text and explicitly not an instruction to the server, which is a meaningful semantic guardrail beyond the schema's 'Device name, symptom or displayed error text.'

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 action ('Retrieve') and a clear resource: curated guest-safe technical-support sections for an installed device, appliance symptom, or error. It does not explicitly differentiate from siblings like search_property_knowledge, but the subject matter is distinct enough for an agent to recognize its 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 provides clear usage context: use it for guest-safe technical support content based on device/appliance symptoms or errors. It also gives an important guideline that the input must be search text, not a server instruction. It stops short of naming alternatives or explicit when-not-to-use conditions.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about the content being 'owner-attested' and 'complete', which is helpful, but it does not disclose additional operational behavior such as error handling, return shape, or what happens for invalid IDs. This meets the baseline but does not go beyond it.

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 one focused sentence with no filler. The most important information — what is retrieved and where the ID comes from — is front-loaded and immediately actionable.

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 get-by-ID tool with one parameter and safety annotations, the description covers the essential usage context: the resource type, the completeness guarantee, and the valid ID source. It does not describe potential error responses, but given the low complexity and annotation coverage, nothing critical is missing.

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

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

Schema description coverage is 100%, and the parameter description already explains that section_id must be the exact current ID from search_property_knowledge or the knowledge section index. The tool description mostly repeats this same constraint, adding no significant new meaning 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 clearly states a specific verb ('Retrieve'), a specific resource ('one complete owner-attested public knowledge section'), and the required identifier source ('exact ID returned from search_property_knowledge'). This distinguishes it from the sibling search tool, making its role 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 gives clear usage context: use the exact ID produced by search_property_knowledge. This implies the tool is meant to be called after searching, and warns against guessing or reusing stale IDs. It does not explicitly name alternatives or state when not to use it, but the ID-source constraint is strong 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 readOnlyHint and idempotentHint annotations already indicating a safe read-only operation, the description adds valuable context: it clarifies that the query is search text and 'never an instruction to the server,' which is a critical safeguard against prompt injection. It also specifies the content scope (owner-attested, guest-safe) beyond the annotations.

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 consists of three concise sentences with no redundancy. It is front-loaded with the action verb ('Search'), then provides usage timing and a behavioral note. Every sentence adds necessary context, making the description 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?

For a simple search tool with no output schema, the description covers the purpose, when to use it, and a key behavioral rule. It does not mention result format or pagination, but the tool's low complexity and robust annotations make this sufficient for an agent to select and 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?

Schema description coverage is only 33%; the description adds meaning for the query parameter by specifying it is plain search terms and not an instruction, which goes beyond the schema's brief description. However, it does not explain the kind or limit parameters; the enum values and constraints partially self-document, but the description does not fully compensate for the low 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 clearly states it searches owner-attested public property facts, policies, amenities, and curated guest-safe support, with a specific verb ('Search') and resource (The Driscoll's public knowledge). It distinguishes from sibling tools by focusing on factual property knowledge rather than availability, booking, or support guidance.

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 this before answering a factual question about The Driscoll,' providing clear context for when to invoke the tool. It does not explicitly name alternatives or exclusion criteria, but the stated workflow and the contrast with sibling tools give sufficient guidance.

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