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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds one genuinely useful behavioral constraint (max 6 combinations) that the schema does not enforce via maxItems, but it says nothing about result ordering, per-combination failures, or cost/latency of fanning out across many combos.

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 front-loaded sentence with zero filler; the scope limit is stated inline where it matters. Nothing could be trimmed without losing meaning.

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?

An output schema exists, so return values need no explanation, but for an 8-parameter, low-coverage tool the description is thin: no mention of round-trip vs one-way handling (return_date), cabin/currency effects, or how ties among combos are resolved. Adequate to call the tool, not to call it confidently.

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 only 38% (3 of 8 params): cabin, adults, currency, max_stops, and return_date are undocumented in both schema and description. The description only gestures at origins/destinations and fares, so it does not compensate for the coverage gap on an 8-parameter 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?

States a specific verb (Compare) and resource (cheapest fare across origin/destination airport combinations), plus a precise scope limit of max 6. It does not name or contrast against the siblings find_cheapest_dates or search_flights, so the agent must infer the boundary between this batch-comparison tool and a single search.

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?

No when-to-use, when-not-to-use, or alternative-tool guidance is given. The agent can loosely infer this is for multi-airport comparison, but nothing tells it how this differs from search_flights or find_cheapest_dates, and the max-6 budget is stated without explaining what happens if exceeded.

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=false, so the safety profile is covered. The description's '(offline)' wording reinforces the openWorldHint=false annotation with useful plain-language context, but adds nothing about result count, pagination, or how ambiguous queries are resolved.

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 front-loaded sentence with the action, the resource, and the accepted input forms; there is no filler to cut.

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?

An output schema exists, so return values need not be explained, and the two-parameter surface is small. The only real gap is that nothing tells the agent how to use 'limit' or what happens with an unmatched query, 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 description coverage is 50%: 'query' is documented in the schema itself, while 'limit' is undocumented in both places, though its default, min, and max make it fairly self-explanatory. The description adds no parameter detail beyond the schema, 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?

States a specific verb ('look up') and resource ('IATA airport codes') plus the input domain ('by city or airport name'), which is enough to separate it from search_flights and find_cheapest_dates. It does not explicitly differentiate itself from compare_airports, which also works on airports, so it stops 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?

There is no when-to-use statement, no mention of alternatives among the siblings, and no stated prerequisites. The '(offline)' note hints at the data source but gives no guidance on when this lookup is the right choice versus compare_airports or search_flights.

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, so the safety profile is covered. The description adds genuinely non-obvious operational behavior: the tool issues one search per day and is capped at 14 days, which tells an agent about cost/latency and a hard input boundary. It stops short of explaining round-trip semantics or what happens when trip_length_days is null.

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 front-loaded sentence with the core action first and the key constraint second. No filler, no restated name or title.

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 output schema exists, so return values need no explanation, and the description covers purpose plus the 14-day limit. But for a 9-parameter tool with an optional round-trip mode (trip_length_days) that interacts with end_date, and with several undocumented parameters, the definition leaves real gaps for correct 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 description coverage is only 56%, and the description adds nothing beyond 'date range', which the start_date/end_date parameters already imply. Parameters such as currency, adults, and max_stops remain undocumented in both places, so the prose does not compensate for the coverage gap.

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 ('Find the cheapest day to fly within a date range'), which is clearly distinct from the sibling search_flights (specific itineraries) and find_airport (airport lookup). It does not name those siblings explicitly, so the differentiation is left to inference rather than spelled out.

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 parenthetical '(one search per day, max 14 days)' implies when the tool is appropriate and constrains the input range, but there is no explicit guidance on when to prefer this over search_flights or compare_airports. Usage is implied rather than directed.

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, so safety and external-data scope are covered. The description adds only the trip-shape and sort behavior, disclosing nothing about result limits (max_results defaults to 10, caps at 30), caching, or availability that would otherwise be invisible.

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 purpose statement is front-loaded in one clean sentence, and the second line is short. The sort_by line is slightly cryptic in form (bare key: values) but contains no wasted prose.

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 12-parameter tool with just 42% schema coverage, the description should carry more weight, especially on passenger-composition semantics and result caps. It does not explain the max_stops/max_results tradeoffs beyond the schema text, nor how it relates to the three sibling search tools; the output schema does relieve it of explaining return values.

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 only 42% of 12 parameters. The description usefully enumerates the sort_by values ('price' default, 'duration', 'departure'), which the schema leaves as a bare string, but it says nothing about adults/children/infants, cabin, currency, or max_results, leaving most parameters unexplained.

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 ('search flights between two airports on a given date') and clarifies the supported trip shapes (one-way/round-trip). It does not, however, distinguish itself from siblings like find_cheapest_dates or compare_airports, so an agent still has to infer which search entry point applies.

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?

Usage is only implied: the agent learns this searches a single origin-destination pair on a date, and the sort_by hint suggests ranking behavior. No when-to-use, when-not-to-use, or sibling routing is given (e.g., use find_cheapest_dates to scan a window).

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