AegeanBot Direct Stays

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 that it returns exact availability, total price, and a booking link, which is useful context beyond annotations. It doesn't mention open-world behavior (e.g., prices may change), but that is already conveyed by openWorldHint=true. The description adds value without contradicting 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 is a single, well-structured sentence that front-loads the core function (availability + price) and includes the key output (booking link). No wasted words; it is concise and immediately informative.

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 (3 required params, read-only, no nested objects) and has an output schema that documents return values. The description covers the main purpose and output. The only gap is the undefined 'listing' parameter, but given the simplicity and rich annotations, the description is largely complete. A score of 4 is justified.

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 67%: checkin and checkout have descriptions, listing does not. The tool description itself adds no parameter-specific details beyond the schema. The baseline for high coverage is 3, and since the description contributes nothing about parameters, this score is appropriate. The listing parameter remains undocumented in both schema and description.

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

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

The description clearly states a specific action: check exact availability and total price for one listing with concrete dates, and includes the direct booking link. This distinguishes it from sibling tools like search_listings (which searches multiple listings) and get_listing_details/policies/faq (which cover other aspects). The verb+resource are explicit.

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 usage when the user has a specific listing and concrete dates, which is a clear context. However, it does not explicitly mention alternatives or when not to use it, nor does it contrast with search_listings. The guidance is implied but not spelled out, so a score of 4 is appropriate.

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 readOnly, idempotent, non-destructive behavior. The description adds context beyond that: it retrieves the host's own Q&A entries and ranks them by relevance ('most relevant') rather than returning exact matches. This helps set expectations for fuzzy/factual lookup 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?

Two compact sentences with no filler. The first sentence front-loads the core action and resource, and the second earns its place by providing usage guidance.

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

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

For a simple read-only lookup with one required parameter, an optional scoping parameter, and an output schema, the description covers the use case, source of data, and selection guidance. Nothing essential is missing 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?

Schema description coverage is 50%: listing_id is documented in the schema, while question is not. The description compensates by clarifying what a question should contain ('factual question about the stay, the house, or the host's services'), but it does not add anything about listing_id beyond the schema's optional-scope wording.

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 ('Retrieve') and a concrete resource ('the host's own Q&A entries'), and it specifies the target questions (factual questions about the stay, the house, or the host's services). This scope is clearly distinct from sibling tools such as get_listing_details or get_listing_policies, even without naming them.

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 signal: 'Prefer this over guessing for any host-specific question.' It does not enumerate exclusions or name alternative tools, but the guidance is enough to route an agent toward this tool for host-specific factual questions.

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, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is fully covered. The description adds the scope (single listing) and the specific facts returned, which is useful but does not disclose any additional behavioral traits like error handling or data consistency. Given the rich annotations, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that states the core purpose and scope with zero wasted words. It is appropriately 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?

For a simple, single-parameter tool with annotations covering safety and an output schema present, the description covers the essential purpose, scope, and content. It lacks explicit guidance on when to prefer this over siblings, but that is partially covered in usage guidelines. Overall it is adequately complete for an agent to call 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 has full coverage (100%) of the single parameter, describing it as a listing title with partial matching allowed. The description does not add any further parameter semantics beyond what the schema already documents, so it meets the baseline but does not enhance it.

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 ('get' implied) and resource ('listing details') with a clear scope ('ONE listing already in play') and enumerates the returned facts (amenities, description, capacity, base price). It distinguishes from sibling tools like search_listings (search vs. existing) and check_availability_and_price (facts vs. availability/pricing).

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 'already in play' implies this is for a listing already identified, not for discovery, which is useful context. However, it does not explicitly name alternative tools or state when not to use it, leaving the agent to infer from sibling names. It gives clear context for use but lacks explicit exclusions.

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

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds value beyond annotations by revealing that the tool returns all policy facts in a single call and that amendment rules are conditional ('when configured'), which is useful 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?

Two efficient sentences, with the core scope and concrete policy facts front-loaded before the usage instruction. Every clause earns its place and there is no redundant repetition of the title or annotations.

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

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

The tool has only one parameter, full schema coverage, helpful annotations, and an output schema, so the description does not need to explain return values. The description provides the scope, the exact policy facts, and a clear usage rule, making it complete for agent 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 coverage is 100% for the single listing parameter, including the note that partial titles are acceptable. The description reinforces the parameter's role by saying 'ONE listing' but adds no meaning beyond what the input schema already provides, so the baseline score 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 states a specific action and result: retrieving every policy fact for one listing, then enumerates the concrete facts (check-in/out times, advance notice, cancellation policy). The 'ONE listing' scoping clearly distinguishes it from broader listing or availability 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 gives an explicit usage rule: 'Use for ANY rules/policy question about a home.' This is clear and actionable, though it does not name sibling alternatives or state when not to use the tool; the rule alone is sufficient for most agent routing.

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 openWorldHint=true, and the description adds context beyond that: results include stable listing IDs for follow-up calls, and the note that availability is checked per night (so a month-long request demands 30 free nights). These are behavioral insights not captured in annotations. It does not describe pagination or result limits, but the output schema likely covers return shape. Given the strong annotation coverage, a 4 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four concise sentences with no filler. The purpose is front-loaded, followed by usage guidance and a pointer to follow-up tools. Every sentence earns its place and the description is appropriately sized for a tool with 19 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?

For a complex search tool with many parameters, the description covers the essential context: what it searches, how to structure input, what not to do, and what the output provides (stable IDs for subsequent calls). The output schema presumably documents the return structure, so nothing critical is missing. The guidance on dates and the monthly-availability edge case is especially helpful.

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 each parameter is already documented. The description adds meta-guidance: to prefer structured fields over free-text query, and to avoid inventing criteria. It also reinforces the special rule about dates (only use exact dates when the guest gave them). This adds value beyond the schema without repeating it, so a 4 is justified.

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 ('Search available vacation rentals across Greece'), and explicitly names the sibling tools for follow-up (get_listing_details, check_availability_and_price), making its role distinct. It leaves no ambiguity about what the tool does and how it differs from 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 gives explicit operational guidance: use structured fields for concrete criteria, reserve query for unstructured preferences, and never invent data the guest didn't provide. It also names the follow-up tools, effectively telling the agent when to move on after searching. This is clear when-to-use and when-not-to-use guidance.

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