City of Trees House

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

Annotations already certify readOnly, idempotent, non-destructive behavior, so the safety profile is covered. The description adds business-level context beyond that: petCount defaults to 0, minimum-stay rules are not evaluated here, no price is produced, and checking does not hold or reserve the dates. Return shape is still undisclosed.

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

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

Three short sentences, front-loaded with the core action, followed by the default and the two most consequential exclusions. No filler or restatement 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?

With no output schema, the description should carry the return contract, and it only partially does: it tells the agent what the result is not (no price, no minimum-stay verdict), implying a simple open/closed answer, but never states the response shape. Everything else an agent needs to call it correctly (dates semantics, guest bounds, pet default, no reservation side effect) is present.

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 each parameter (guests 1-10, checkIn America/Los_Angeles YYYY-MM-DD, exclusive checkOut, petCount 0-2) is fully documented in the schema. The only param note in the description, the petCount default, merely repeats the schema, so the baseline of 3 applies.

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

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

States a specific verb (check) and outcome (whether the house is open) scoped to checkIn, checkOut, and guests. The negations (no price, no minimum-stay check) implicitly separate it from get_quote, but no sibling is named outright, so differentiation is inferential rather than 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?

Gives usable negative guidance: no minimum-stay validation, no price returned, and dates are not reserved, which tells the agent this is a tentative availability probe rather than a booking/quote step. It stops short of naming get_quote or get_booking_link as the follow-up tools, so the routing is left to inference.

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

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds real value beyond that: it tells the agent the actual next action belongs to the guest on the website (totals review, payment authorization, identity verification), which prevents the agent from attempting those steps through tools. It does not mention link expiry or return shape.

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 short sentences, front-loaded with what the tool returns and then the workflow constraint. Every sentence carries weight (link, stop point, guest actions, no payment/ID here). Slightly repetitive in restating that payment and ID are outside the tool, but not wasteful.

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

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

For a low-complexity link-returning tool with full schema coverage and annotations covering the safety profile, the description supplies the missing operational context: where the agent's role ends and the guest's begins. With no output schema, the only mild gap is that it doesn't describe the link's nature (single-use, expiring, session-bound).

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% — checkIn, checkOut, guests and petCount each carry inline descriptions with patterns, ranges, defaults, and the America/Los_Angeles timezone note. The description adds nothing about parameters, so the baseline 3 applies when the schema does all the work.

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

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

States a specific verb and resource: 'Return a City of Trees House checkout link for the stay.' It clearly separates itself from a quote/availability tool by noting payment and ID verification happen off-platform. It stops short of naming any sibling tool (get_quote, check_availability) as an alternative, so it is clear but not explicitly differentiated.

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 assistant must stop here' is an explicit terminal instruction, plus 'No payment or ID check through this tool' sets a firm boundary on what this tool must not be used for. It lacks explicit naming of the preceding step (e.g., use get_quote first), but the workflow handoff is unambiguous.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is fully covered. The description adds useful scope context by clarifying what is NOT returned ('No live price'), but it says nothing about return format, freshness, or data source beyond the field 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?

A single tight sentence front-loads the resource and field list, then closes with the key exclusion. There is no filler and every clause 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?

There is no output schema and no parameters, so the description carries the burden of explaining what is returned — and it does enumerate the key fields. It is nearly complete, missing only return structure/detail that would help an agent parse the response.

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

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

The tool takes zero parameters and schema coverage is 100%, so no parameter documentation is required. The description correctly focuses on return content instead. Baseline 4 applies for a parameterless 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?

Clear verb+resource: retrieves public facts about a specific property (City of Trees House) and enumerates the returned fields (occupancy, bedrooms, bathrooms, pets, stay bounds, booking links). It is distinguishable from check_availability and get_quote, though the mention of 'booking links' overlaps with the get_booking_link sibling, creating minor 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 phrase 'No live price' implies this tool should not be used for pricing (use get_quote instead), which is weak implied routing. There is no explicit when-to-use statement or named alternative, leaving the agent to infer the relationship between this and check_availability/get_booking_link/get_quote.

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 the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false), so the extra burden is low. The description still adds genuinely useful behavior the annotations cannot convey: a 30-minute expiry on the quote, no date reservation, and payment handled off-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?

Two tight sentences that front-load what is returned before the caveats, with every clause carrying information (inputs, expiry, no-reservation, payment location). Nothing is padded.

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

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

With no output schema, the description does state what comes back ('quote and payment totals') and flags the 30-minute validity, which is the key operational caveat. The exact shape of the returned quote is left unspecified, a minor gap for a read-only pricing call.

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 format, ranges, and defaults for all four parameters. The description's mention of petCount defaulting to 0 and the core inputs merely restates schema content, adding no new syntax or edge-case meaning.

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

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

States a specific verb and resource ('Return a live PriceLabs quote and payment totals') with the exact inputs that drive it. It implicitly separates itself from a booking tool by clarifying it 'does not reserve dates,' which helps against get_booking_link, but no sibling is named explicitly.

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

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

The description implies the use case (getting live pricing before committing to a stay) and rules out reservation/payment, but never states when to prefer this over check_availability or get_booking_link, nor any prerequisites. Usage is inferable rather than guided.

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