American Ghost Walks

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

Annotations already declare the safe read-only, idempotent nature, so the description adds useful context beyond them: times are local to the tour, availability may be unknown, and the agent should not guess when no times are listed. It does not describe return structure or permission requirements, but it covers the key behavioral caveat for this 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 front-loaded with the core purpose and local-time caveat, then immediately gives operational guidance and a fallback. Every sentence contributes to correct tool selection or invocation.

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 identifies the key return content (open departure times and booking status) and warns about unknown or empty results. It is complete enough for an agent to choose and call the tool, though a fuller return-shape description would make it stronger.

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 100% description coverage for tour, date, and party_size, so the description does not need to duplicate parameter details. It reinforces the one-tour/one-date scope and local-time meaning, but adds little 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 states a specific verb and resource: retrieving open departure times and booking status for one tour on one date from the American Ghost Walks booking system. It clearly scopes the operation to a single tour/date pair, which distinguishes it from siblings like search_tours and get_tour_details.

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 gives explicit when-to-use guidance: check this before telling a guest a time is open. It also names the alternative behavior when availability is unknown or no times are listed: send the guest to the booking link instead of guessing.

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, idempotent, non-destructive behavior. The description adds meaningful context beyond them: the transaction happens externally on the booking page, nothing is held or charged, and the URL must be relayed verbatim. It doesn't mention link expiry or stability, but the core behavioral picture is solid.

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 what is returned, followed by the transaction boundary and the output-handling rule. No filler or repetition.

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?

Four parameters, no output schema, full schema coverage, and rich annotations. The description fills the remaining gap by describing what the return contains and how to use it, and by making clear the tool is a pointer to an external checkout rather than a booking commit.

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 docs are already strong, including the HH:MM format warning and the tour_id cross-reference. The description adds nothing parameter-specific, so the baseline 3 for high-coverage schemas 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?

Specific verb and resource: 'Returns the official American Ghost Walks booking link for a tour, plus what to pick on its calendar.' It's clearly a link-generation tool, distinct in kind from get_availability or search_tours, though 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?

Draws the boundary clearly: 'The guest chooses the date, time and tickets and pays on that page; this tool does not reserve or charge anything,' which tells the agent this is not a booking action. It also instructs how to handle the output ('Share the returned URL exactly as given'). No explicit alternative-tool routing is given.

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, destructiveHint=false and openWorldHint=false, so safety and determinism are covered structurally. The description contributes the substantive behavior that matters — the closed-corpus constraint ('answer only from what this returns') and the phone-number fallback. It does not describe error behavior for an unknown tour slug, so it adds value but not rich context beyond 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?

Three sentences, front-loaded with the payload inventory, then usage intents, then the grounding constraint. The field enumeration is long but each item is a distinct answerable topic an agent would otherwise have to guess at. Little waste.

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 a single parameter, the description carries the full burden of describing the return payload, and it does so by naming each content section. Combined with the grounding rule and the fallback path, an agent has everything needed to call it and to handle an incomplete answer.

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 already explains that 'tour' takes a slug from search_tours.tour_id or an exact name, including an example. The description adds nothing about the parameter, so the schema does all the work and baseline 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?

Opens with a specific verb+resource ('Full details for one tour') and enumerates exactly what comes back — description, stops, meeting spot with map link, duration, difficulty, FAQ, policies, rating. That makes it clearly distinguishable from search_tours by scope (one tour vs. search results), though the description itself never names the sibling tools; the linkage appears only in the schema's reference to search_tours.tour_id.

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 concrete example intents ('how much walking is it?', 'can kids come?', 'where do we meet?') that map directly onto the returned fields, and adds an explicit exclusion/fallback: answer only from what this returns, otherwise give the phone number. This tells the agent both when to use it and what to do when it is insufficient.

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, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior: the empty-city enumeration mode and the fact that departures are only returned when dates are supplied. It does not cover result ordering, pagination or the empty-result case.

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, zero filler, and the primary capability plus return payload are front-loaded before the edge-case guidance. Every sentence carries information an agent can act on.

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 correctly takes on the job of describing the return payload (ids, names, descriptions, duration, meeting spot, price, departures). It is nearly complete for a 4-param search tool; only pagination and no-results behavior are unaddressed.

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%, and the schema already documents the city examples, the 14-day end_date window, the 1-50 party size range and that start_date requires city. The description's parameter statements (date range, party size, no-city listing) largely restate that, so the baseline 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?

The description opens with a specific verb and resource ("Find American Ghost Walks ghost and history walking tours") and states the filtering axes (city, date range, party size). It hints at the sibling relationship by saying to reuse a tour id "with the other tools," but never names get_availability, get_tour_details or get_booking_link, so the agent still has to infer which sibling follows.

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?

Clear usage context is given: call with a city to filter, call with no city to enumerate everything, and add dates/party size to surface open departures. What's missing is an explicit contrast — nothing says when to skip this tool and go straight to get_availability or get_tour_details instead.

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