Altivo Jets

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds value beyond them by enumerating what does NOT happen: no booking, hold, or payment is created and no traveller details are sent to Altivo. That data-sharing and side-effect disclosure is exactly the context annotations cannot carry.

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 with zero filler; the core action is front-loaded and the safety caveat follows immediately. Nothing could be cut without losing 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?

For a simple read-only link generator with no output schema and a fully documented single param, the description is nearly complete. Minor gaps remain: it doesn't state that the return value is a URL/link, nor anything about link validity or expiry.

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?

Only one parameter, and schema coverage is 100% ('Leg reference from search_empty_legs' already documents origin and format). The description adds nothing about the ref beyond what the schema says, 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 and resource: returns the altivojets.com page for reviewing an empty leg and submitting a booking request. It clearly distinguishes itself from siblings like search_empty_legs (find legs) and request_quote (agent-initiated booking) by making the self-service handoff 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?

Usage is implied rather than stated: the traveller sends the request themselves, which contrasts with request_quote, but no sibling is named and no explicit when-to-use condition (e.g. 'call after search_empty_legs when the traveller wants to book directly') 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 establish read-only, idempotent, closed-world, non-destructive behavior, so the bar is lower. The description still adds real context: the data is authoritative (regulators' published lists) and it clarifies the permit taxonomy (scheduled airline holds a scheduled permit, not a charter permit), which prevents misinterpretation of results.

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 compact sentences, front-loaded with the resource and what it returns. The permit-kind clarification and sibling handoff each carry weight; 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 usefully enumerates the fields an agent will get back, and the permit-kind note covers the main ambiguity in results. Pagination/ordering behavior is unstated, but the limit parameter and annotations cover most of what an agent needs to call this 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 coverage is 100%, so city, limit, market, and category are fully documented there. The description only restates that filtering is by market, base city, or aircraft size, adding conceptual framing but no syntax or edge-case detail 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?

States a specific retrieval ('Licensed operators from the regulators' published lists') with the filter dimensions and even enumerates the returned fields (name, base city, licence type, permit kind, fleet, models, profile page). It distinguishes itself from request_quote by framing that tool as the trip-booking path.

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 routes the agent away from this tool for trips ('For trips, use request_quote'), which is a real when-not-to-use rule. It doesn't address other siblings like list_aircraft or list_markets, but the schema already points to list_markets for valid market values.

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 this a read-only, idempotent, non-destructive, closed-world fetch, so the safety profile is covered. The description adds genuinely useful context beyond that: it discloses which spec fields come back only 'where the listing gives them' (i.e., partial data is possible), that the seller is never named, and that the desk confirms specs with the seller's broker — though it says nothing about error behavior for an invalid reference.

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 sentences, front-loaded with the resource and followed by the disclosure caveat about the seller. The long parenthetical spec enumeration is dense but earns its place by previewing the payload given there is 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?

For a one-parameter, read-only tool with full schema coverage and no output schema, this is complete: it describes the returned contents field-by-field and flags the two things an agent could otherwise get wrong — missing specs and the anonymity of the seller.

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 parameter is documented with a concrete format example and the alternative page-address form, so the schema carries the load. The description's phrase 'by its reference' restates rather than extends that meaning, 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 names a specific verb+resource: it returns one aircraft-for-sale listing by reference, and enumerates what the payload contains (engines and times, APU, airframe cycles, avionics, maintenance, interior/exterior, page link). That clearly separates it from list_aircraft and search_aircraft_for_sale, though neither sibling is named explicitly, keeping it just 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?

Usage is only implied: 'by its reference' signals this is the detail fetch that follows a search, and the schema's example reference 'from search_aircraft_for_sale' reinforces that, but the description itself gives no explicit when-to-use or when-not-to-use guidance versus search_aircraft_for_sale or list_aircraft.

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, so the bar is lower; the description still adds real context: pricing is indicative and excludes the exclusions named (positioning, landing, handling), rates mirror the public altivojets.com calculator, and currency follows the departure market. It does not cover auth, rate limits, or latency, so it is not a 5.

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 pricing scope before the output inventory and the estimate-vs-quote caveat. Dense but nearly every clause carries information; the enumeration of outputs is long but necessary in the absence of an 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 carries the return-shape burden and discharges it fully by listing every return field, plus the estimate/quote caveat. For a read-only 7-param tool with full schema coverage, nothing an agent needs to invoke 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%, so the baseline is 3, but the description adds meaning the schema does not: the default currency is the local currency of the departure market unless the currency param overrides it, and the price is driven by aircraft size and one-way vs. return. These map to aircraft_category, return_date, and currency beyond the schema's own wording.

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 ('indicative full-charter price') and enumerates the exact outputs: price range before taxes, estimated taxes, all-in range, flight time, fuel stops, recommended size. This clearly separates it from siblings like request_quote and find_operators, which an agent can distinguish 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?

The closing sentence gives explicit positioning: 'An estimate, not a quote: the operator's quote confirms positioning, landing and handling.' This tells the agent when this tool is the right choice versus a firm quote. It stops short of naming the request_quote sibling directly, so the routing is clear but not fully explicit.

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 read-only, idempotent, non-destructive and closed-world, so the description's added value is the availability semantics: the record is 'live' and 'says it is no longer available once booked, withdrawn or flown'. That tells the agent to expect a stale/invalid outcome rather than a hard error — genuine context beyond the structured hints, though it omits what an unavailable result looks like.

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 with zero filler: the identity and lookup key come first, the availability caveat second. Nothing is repeated from the title and every clause 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 must hint at the return: it discloses that pricing is party-size dependent and that the leg can report as unavailable. What the response actually contains (fields, aircraft, route) is left unstated, a minor gap for a single-record fetch.

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 baseline is 3; the description earns a bump by tying 'priced for the party size' to `passengers`, explaining that party size affects the returned price — a causal link the schema does not state. `currency` and the exact ref format remain schema-only.

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 ('Re-read one live empty leg') plus the keying mechanism ('by the `ref` a search returned'), which implicitly distinguishes it from search_empty_legs and booking_handoff. It stops short of naming the sibling outright, but an agent can still tell what this does.

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 implied rather than stated: 'the `ref` a search returned' tells the agent a prior search is required, and the schema confirms search_empty_legs is the source. There is no explicit when-not guidance or mention of alternatives such as re-running the search instead of re-reading.

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, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds that rates are 'indicative', which is useful context, but does not disclose pagination, full return shape, or filtering behavior beyond what the schema implies.

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 efficient sentence that front-loads the resource and enumerates attributes. No redundancy, though it could be slightly more structured with a leading verb.

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 gives a reasonable idea of return fields (seats, range, rate, models) but omits pagination and the exact format. For a listing tool with annotations covering safety, it is adequately but not richly complete.

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 both parameters are already documented, including the enum for category and the market example. The description adds that the market is the market where models are most flown, but does not explain the filter semantics 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 the resource (aircraft sizes) and its attributes (seats, range, hourly rate, models), and names the specific category range. It doesn't explicitly differentiate from siblings like get_charter_estimate or find_operators, but the resource is clearly distinct.

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 explicit when-to-use or when-not-to-use guidance, and no alternatives named. The schema indicates both parameters are optional, implying a broad listing, but the description does not state that it returns all aircraft when unfiltered.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description's added value is the shape of the returned data (fields per market), but it says nothing about caching, stability of the market list, or auth requirements, so it adds only modest context.

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 compact sentence with no filler, and the most informative part (what each market entry contains) is front-loaded. It is a noun fragment rather than a complete statement of action, a minor structural weakness.

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 carries the burden of describing return values, and it does enumerate the fields returned per market. For a static, well-bounded reference list that is close to sufficient, though it omits ordering, count, or whether pagination applies.

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 no parameters, and the schema confirms an empty object with additionalProperties false, so there is nothing for the description to clarify. Baseline 4 applies for a zero-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?

The description names the resource (countries Altivo Jets serves) and enumerates the payload (currency, aviation regulator and licence, local site and empty legs page). The listing verb is only implied by the name rather than stated, and it does not explicitly distinguish itself from siblings like list_routes or find_operators, though the resource set is clearly disjoint.

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 or when-not-to-use guidance and no named alternative among the siblings. For a zero-parameter enumeration tool the invocation is unambiguous, but the description leaves the agent to infer the context entirely.

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 this a safe, idempotent, non-destructive read, so the description's job is to add context—and it does: results are ordered by search demand and each entry carries a from price, typical aircraft, flight time, live empty legs, and a guide page URL. With no output schema, this disclosure of return shape is the main behavioral value it provides.

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 densely packed sentence with the resource and ordering front-loaded and no filler. The trailing enumeration of fields is long but each item is informative for an agent that has 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?

For a read-only, zero-required-parameter list tool with annotations covering the safety profile, the description supplies the missing return-shape information that the absent output schema would otherwise carry. The remaining gap is routing guidance toward the empty-leg and market siblings, which is not covered anywhere.

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 limit, market, and origin are already fully documented with examples and defaults. The description adds only the implied 'by market' filtering dimension, which the schema already states—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?

The description names a concrete resource ('popular private jet routes'), its scoping dimension ('by market'), and its ordering ('by search demand'), so an agent can tell it apart from list_markets or search_empty_legs. It reads more as a description of the returned collection than as an action verb, and no sibling is named explicitly, which keeps it just 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 or when-not-to-use guidance and no alternative tool is named, even though siblings like list_markets and search_empty_legs overlap in subject matter. Usage must be inferred entirely from the fact that it lists popular routes.

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 a non-read-only, open-world, non-idempotent, non-destructive call. The description adds real context beyond that: the request goes to a human sales desk, the buyer is contacted by email or phone with price, specs and records, and nothing is reserved, offered or agreed. That last clause usefully bounds the side effects, though it does not discuss timing or failure handling.

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 core action and its two modes are front-loaded in the first sentence, followed by the precondition and the non-binding disclaimer. It is dense but every clause carries information; the opening sentence is long and could be split for readability.

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 carries the burden of explaining what happens after the call, and it does: the desk contacts the buyer with asking price, specs and records. Combined with the precondition and the non-binding statement, an agent has everything needed to decide and invoke 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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: supplying a reference means interest in a specific aircraft, while omitting it and describing the aircraft in the question turns the call into a find-request. That conditional relationship between two parameters is genuinely useful.

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: it sends a buyer's interest in a listed aircraft, or a find-request, to the Altivo Jets sales desk. It also distinguishes the two modes (with reference vs. without reference) and is clearly separable from siblings like search_aircraft_for_sale or request_quote.

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 an explicit gating condition: call only when the buyer asks to be contacted, after confirming name and email. That is strong when-to-use guidance. It does not explicitly name an alternative tool for the case where the buyer does not want contact, which keeps it just short of a 5.

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 declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, but say nothing about consequences. The description adds real value by stating no payment is taken and nothing is booked or held, and that a human specialist follows up to confirm aircraft, availability, price and operator. It does not warn that repeated calls create duplicate requests (idempotentHint=false), which is the one notable remaining gap.

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 tight sentences, front-loaded with what the tool does, followed by the outcome, then the negative constraints, then the usage condition. No filler and each sentence carries distinct 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?

For an 11-parameter, non-read-only request tool with no output schema, the description covers the essential unknowns: what is sent, who acts next, that no money or hold is involved, and the precondition for calling. Nothing an agent needs in order to call this 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. The description adds selection semantics beyond the schema by explaining that empty_leg_ref switches the request to a specific empty leg rather than a general charter, and that name/email are the confirmation channel — useful framing the field-level descriptions do not establish.

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: send trip/contact details to the Altivo Jets desk for a full charter or a specific empty leg. It also disambiguates from siblings like get_charter_estimate and booking_handoff by making clear this is a request-for-contact rather than a price lookup or a completed booking.

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 a clear precondition — 'Use only when the traveller asks Altivo to contact them, and confirm their name and email first' — plus the selector between modes (full charter vs. specific empty leg via empty_leg_ref). It does not explicitly name the alternative tools (e.g., get_charter_estimate for instant pricing), so it falls short of full routing guidance.

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 this as a non-destructive, idempotent read with openWorldHint=false, so the safety profile is covered. The description adds substantive behavior beyond that: default and maximum result count, newest-first ordering, the exact fields returned, a note that price-on-request listings are excluded when price_max is used, and the co-brokered/seller-anonymity disclosure. That last point is non-obvious domain behavior an agent could not infer from structured fields.

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 dense sentences that front-load the purpose before detailing filters and return shape, with essentially no filler. The only waste is the redundant 'US only' constraint repeated at the opening and the close, which slightly dilutes an otherwise tight definition.

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, so the description carries the burden of explaining returns — and it does, listing year, model, serial number, total time, location, price (or price on request), and the listing page, plus ordering and the limit default. For an eight-parameter optional-filter search tool, nothing an agent needs in order 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%, so every parameter is already documented with examples and ranges, which sets the baseline at 3. The description restates the filter axes (type, make, model, state, year range, max price) but adds little syntax or meaning beyond the schema, apart from clarifying that price_max drops on-request listings — which the schema also states.

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+resource ('Search aircraft for sale') and immediately scopes it to the United States, naming the aircraft categories covered and the exact filter dimensions. It is distinguishable from siblings such as list_aircraft and get_aircraft_listing because it is explicitly a filtered search over for-sale inventory.

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 context is clear: this is the tool for finding aircraft for sale in the US, with the supported filter axes enumerated. The 'US only' exclusion is stated twice, which is a real constraint on when it applies. What's missing is explicit routing to alternatives (e.g., when to prefer list_aircraft or get_aircraft_listing), so it stops short of a 5.

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 earns credit by adding things annotations cannot: results cap at limit (default 5, max 20), prices are whole-aircraft in local currency with estimated taxes and an all-in estimate, operators are deliberately withheld, and inventory churns so results should be re-run rather than cached. That is substantive behavioral context beyond the structured fields.

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 what/where, then what comes back, then the freshness rule. Dense but each clause carries information. The long enumeration of return fields is slightly list-heavy, though it is doing real work given there is 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 correctly compensates by enumerating the returned fields (route, departure window, aircraft, seats, price, taxes, all-in, charter comparison, booking link). The one gap is that all nine parameters are optional, yet the description never states which inputs are effectively needed to get meaningful results (e.g. origin/destination/date window).

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 all nine parameters including formats, bounds and examples; the baseline of 3 applies. The description merely restates the high-level dimensions and the default/max limit, adding no format or interaction detail beyond what the schema provides.

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 live empty leg flights') and immediately defines the domain term parenthetically as 'whole aircraft, discounted repositioning flights'. The description also scopes the search axes (origin, destination, date window, passengers, market, price ceiling), which cleanly distinguishes it from the single-record sibling get_empty_leg and the pricing sibling get_charter_estimate.

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 implied by the search axes and by the note that operators are not named, which tells the agent when this tool won't answer a 'which operator' question. However, no sibling is named and no explicit when-to-use / when-not-to-use condition is given (e.g. 'use get_empty_leg once you have a specific leg id, use get_charter_estimate for non-empty-leg pricing').

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