Fly Frugal Travel Data

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavior: the paid guide body is never returned, and an unknown slug produces an error rather than empty output.

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?

Front-loads the action and identifier, then the return contract and the error case, in a compact paragraph with no filler. The field enumeration is slightly list-like but earns its place given no output schema.

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 takes on the return-value burden and does so: it names the returned fields, states the boundary condition (no full guide), and documents the failure mode. Nothing needed to call it correctly 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 coverage is 100% and the single slug parameter is fully documented (pattern, maxLength, examples) in the schema itself. The description only restates that the slug comes from list_itineraries, adding no format or syntax detail beyond the schema — baseline 3.

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+resource (get one itinerary preview by slug) with explicit scope narrowing ('public preview', 'the complete paid day-by-day guide is never returned'). It distinguishes itself from list_itineraries by name, so an agent can route without opening a schema.

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 clear intended uses ('describe a trip to the user', 'decide whether the full guide fits') and identifies list_itineraries as the source of the slug. It stops short of an explicit 'if you want all itineraries, call list_itineraries instead' exclusion, so it's clear context without full alternative 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description wisely spends its budget on semantics the annotations cannot express: the exact calendar-day/timezone definition of 'today', the verification criterion (positive saving vs usual price), and the empty-list behavior. It even discloses an extra return field ('plus count').

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 sentences with no waste: the filtering rule comes first, then the usage trigger, then the return shape, then the fallback. Every sentence carries distinct information and the routing guidance 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?

Despite having no output schema, the description explains the return shape by reference to a sibling ('same fields as list_flight_deals, plus count') and covers the degenerate empty case. For a zero-required-parameter read tool, nothing an agent needs to call it correctly 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%, with limit, nights and origin each fully documented including ranges, defaults and the IATA pattern, so the schema does the heavy lifting. The description adds no syntax or meaning beyond the schema for these three parameters, which is the baseline 3 case.

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 ('Return only the strongest current deals') and pins the exact filter: fares whose Google savings insight was checked today (America/Los_Angeles) with a positive saving versus usual price. It also distinguishes itself from the sibling list_flight_deals by framing that tool as 'recent observations' rather than freshly verified deals.

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?

Explicit when-to-use ('when the user asks for today's deals or wants prices that are freshly verified') plus a named alternative and the condition that selects it ('offer list_flight_deals for recent observations'). It also instructs on the empty-result case, telling the agent to say so rather than present older fares.

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=false, so safety is covered. The description adds genuinely non-structured context: prices are observations that can change or sell out, and the agent should tell users to confirm before booking. It omits pagination behavior, but that is minor for a bounded list 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?

Front-loaded with purpose and scope, then the sibling routing rule, then return fields. The long enumeration of returned fields is justified given there is no output schema, though it makes the description dense; every clause still carries 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?

With no output schema, the description supplies the return-field inventory (origin, destination_airport, price/currency, google_price_signal and related fields), the freshness caveat, and the sibling alternative. An agent has everything needed to invoke and interpret results 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 100%, so all three parameters (limit, nights, origin) are already fully documented, including omit-to-search-all behavior. The description's mention of "one departure airport or across all tracked US airports" only restates the schema, adding no new syntax or constraints; 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?

States a specific verb (list) and resource (cheapest round-trip economy fares), with scope spelled out: from one departure airport or across all tracked US airports. It names the sibling get_todays_deals and the condition distinguishing it, so an agent can pick correctly without opening either schema.

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 trigger examples ("cheap flights from SFO", "where can I fly for under $500") plus an explicit routing rule: for deals re-verified today, use get_todays_deals. Both when-to-use and the alternative are stated, not inferred.

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 the description goes well beyond that by disclosing result ordering (newest first) and a data-scope exclusion (only public previews, the paid full guide is never included). Since there is no output schema, enumerating the returned fields is genuinely additive rather than redundant.

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 tightly packed sentences with the routing instruction front-loaded ahead of the field inventory. Every clause carries distinct information (purpose, alternative tool, returned fields, ordering/scope) and none restates the name 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?

With no output schema, the description adequately covers return contents, ordering, and visibility limits, and the schema covers both inputs. The one gap is pagination behavior: nothing explains how to retrieve results beyond the limit or whether a cursor exists, which matters for a 50-item-max listing.

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 both parameters (limit, country) are already documented with ranges, defaults, matching rules, and examples in the schema. The description adds no additional syntax, default, or matching nuance beyond what the schema provides, 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+resource (browse published Fly Frugal itineraries) and immediately scopes it as a discovery/listing operation rather than a detail fetch. It explicitly names the sibling get_itinerary and the handoff condition (pass a returned slug), so an agent can distinguish the two without opening either schema.

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?

"Use this to discover which destinations have a guide, then call get_itinerary with a returned slug for one guide's preview" gives an explicit when-to-use and names the alternative tool with the exact linkage value. The workflow (list first, then fetch by slug) is fully specified, leaving nothing to inference.

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