flight-fares

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that prices are cached snapshots and never live quotes, dictates the correct phrasing ('last observed', never 'current price'), and instructs surfacing live_check_url to any user about to book. That is exactly the data-freshness and downstream-action context an agent needs.

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 return payload, then usage triggers, then the directional/required-argument constraints, then the caching caveat. Every sentence carries distinct, non-redundant information with no filler.

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 annotations and no output schema, the description compensates by describing what comes back (cheapest fare, six-month low, observation date, live_check_url) and how to present it. Nothing needed to call or interpret the tool 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%, so the baseline is 3, but the description adds semantics the schema does not: the relationship is directional and per-pair (PAR to BKK is not BKK to PAR, and is not PAR to SIN), and both arguments are jointly required. That materially affects correct invocation.

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 (Returns), resource (cheapest observed one-way fare between two cities), and even enumerates the payload (six-month low and its observation date). It is trivially distinguishable from list_routes_from and resolve_city.

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 explicit trigger conditions: the user names an origin and destination and asks about price, cheapest date to fly, or whether a fare is a good deal. It also flags that both arguments are required and neither alone works. It stops short of naming alternatives or when-not-to-use cases in the description text (the resolve_city routing lives only in the schema).

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 no annotations, the description carries the full burden. It discloses that results are sorted cheapest first and that prices are cached snapshots, which is useful. However it doesn't state permission/auth needs, rate limits, or what happens with no reachable destinations, leaving gaps for a read 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?

Three compact sentences, front-loaded with the core behavior and sort order, followed by usage context and an efficiency note. No filler; each sentence 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?

For a simple 2-param read tool with full schema coverage and no output schema, the description covers purpose, sort order, usage context, and a pricing caveat. It is nearly complete, missing only auth/error behavior, which keeps it from a 5.

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 schema already documents both 'from' and 'limit' with format, units, and default. The description adds no parameter detail beyond what the schema provides, so baseline 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?

States a specific verb+resource (returns destinations reachable from one origin) and adds a distinguishing detail (sorted cheapest first). It implicitly contrasts with find_cheapest_fare by framing inspiration vs one specific pair, but does not name the sibling outright, so it falls short of a 5.

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 when-to-use cues: 'when the user asks where they can fly cheaply from a city, or wants inspiration rather than one specific pair.' This clearly delineates it from find_cheapest_fare, though it doesn't explicitly name the alternative tool or state 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?

With no annotations to lean on, the description carries the burden and does disclose the output shape (uppercase IATA code) and a hard constraint against fabricating codes. It omits behavior for unresolvable or ambiguous names, so it is strong but not exhaustive.

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 transformation, then the ordering rule, then the constraint. No filler; every sentence 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?

For a single-parameter resolver with no output schema, the description supplies the missing return contract (uppercase IATA code) and call ordering. The only gap is unspecified handling of unknown or ambiguous queries.

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 schema already explains 'query' as a city or partial name. The description reinforces that input may be spoken-style, adding slight value, but there is little beyond the schema to convey.

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 precise verb+resource (turn a spoken city name into an uppercase IATA code) and names the exact output contract other tools expect. It is clearly distinguishable from find_cheapest_fare and list_routes_from.

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?

Explicitly tells the agent when to call it (before find_cheapest_fare, whenever uncertain of a code) and adds a negative rule ('Do not invent codes'), which routes behavior away from hallucinating codes.

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