BEACON by Owner Connect

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new behavior: it returns free/taken per day and never the actual schedule, it is not a hold or confirmation, and it returns a reason instead when the owner does not publish availability. These return-content and failure-mode disclosures are exactly what annotations cannot convey.

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 and every sentence carries information (scope, trigger, return format, exclusions, error case). However, phrasing is awkward and indirect ('read from the live schedule its owner connected', 'answer with its sentence'), which costs clarity for an agent parsing it quickly.

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-value burden and does so: per-day free/taken, never the schedule detail, plus an error-path result. Parameters and scope are covered. Only minor polish is missing, so it is effectively complete for this tool.

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 meaning beyond the schema by tying date to the departure date, end_date to a return trip, and imposing a 14-day span limit that the schema itself does not state. That extra constraint lifts it above baseline.

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: checks whether one aircraft has anything scheduled on a date or a span of up to 14 days, reading the owner's live schedule. The scope (single tail, 14-day max, live data) is precise. It doesn't explicitly name a sibling it replaces, but the purpose is unmistakable against estimate_charter or request_trip.

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 an explicit trigger ('Call it when the person you are helping asks whether the aircraft is available') and the arguments to supply for one-way vs return trips. It also draws boundaries ('Not a hold and not a confirmation'). No named alternative tool is offered, so it falls 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, open-world), and the description adds substantial behavior beyond them: positioning is included when the owner bills it, block hours derive from owner block speed, and it returns 'a reason instead of a figure' when no charter terms or rate exist. This degraded-path disclosure is exactly the kind of 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?

Purpose is front-loaded, but the middle sentences are long and run-on, and 'Answer with its sentence' is cryptic without more context. The content earns its place but the phrasing could be tighter.

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 does the work of explaining what comes back: a cost sentence, or a reason instead of a figure. Combined with the fallback behavior and parameter conditions, an agent has enough to call it correctly, though the exact response shape remains vague.

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 real meaning: block_hours is only for use when the owner set no block speed and is ignored when from/to are given. It clarifies the conditional relationship between parameters rather than just restating them.

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: computing an approximate charter cost for one aircraft at the owner's published hourly rate. The 'approximate... not a quote' framing clearly separates it from a booking tool like request_trip, though it never names a sibling 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?

Gives an explicit trigger ('Call it whenever the person you are helping asks what a trip would cost, with the departure and arrival airports') and a clear retry rule when no block speed is published, using block_hours. It does not explicitly route the user to request_trip for an actual quote, so it stops short of naming alternatives.

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, openWorld, non-destructive), so the bar is lower. The description still adds real value beyond them: the enumerated status outcomes (found, not_found, invalid, unavailable) and the conditional presence of owner_approved disclose response behavior the annotations cannot.

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 what the tool returns before detailing field semantics. The closing case/hyphen sentence duplicates the schema description, so it is not perfectly waste-free, but overall density is high.

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-value burden and does so by naming each top-level field and explaining when owner_approved appears. For a one-parameter lookup, 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 coverage is 100% and the single 'tail' parameter is fully documented there. The description's note that case and hyphens are ignored merely repeats the schema's own wording, adding no new syntax or format guidance. Baseline 3 applies when the schema does all the work.

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 resource (one U.S. registration mark) and enumerates exactly what comes back (status, public_record, owner_approved), so the agent knows this is a single-aircraft lookup rather than a search. It never names search_aircraft explicitly, so sibling differentiation is inferred from the 'one registration mark' framing rather than stated.

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 singular 'one U.S. registration mark' scope, which contrasts naturally with the list-shaped search_aircraft sibling, but there is no explicit when-to-use or when-not-to-use guidance. Nothing tells the agent when to prefer check_availability or search_aircraft instead.

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?

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing the full side-effect chain: nothing is booked or held, the requester is emailed a confirmation link, the request is only delivered after they confirm, and the booking contact replies directly. It also documents the two-call qualification-question protocol, which 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?

Front-loaded with what the tool does, then the precondition, then the behavioral chain, then the exception flow. Every sentence carries distinct operational 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 output schema and 11 parameters, the description supplies exactly what structured data cannot: the gating precondition, the non-committal behavior of the request, and the needs_answers two-step flow. An agent has everything needed to call it 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; the description earns an extra point by explaining the semantics of `answers` (must be supplied in the order returned by the first call) and by tying `name`/`email` to the identity of the person being helped, both of which the schema only hints at.

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 and resource: "Sends a charter trip request for one aircraft to the booking contact its owner named." The recipient and the non-binding nature of the request clearly separate it from siblings like check_availability, estimate_charter, and send_buyer_inquiry.

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 an explicit precondition — call only after the person has asked to proceed, with their own name and email — plus the conditional branch for qualification questions (first call returns needs_answers, then call again). It does not explicitly name which sibling to use instead when the user is still exploring, so it stops short of 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 declare read-only, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: filters only apply to owner-cleared facts, so an unpublished seat count never matches a seats filter — this prevents the agent from misreading empty results as 'no such aircraft'. It also names the returned owner_approved block despite no output schema.

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 scope and filter list, then the critical caveat, then the return shape and the sibling alternative. No sentence is filler; each carries either scope, a filter caveat, or routing 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 compensates by naming the returned owner_approved block, and all parameters are covered by the schema. It omits result ordering/pagination behavior beyond the limit cap, which is the only material gap for a list tool.

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 six parameters (type, limit, charter, for_sale, min_seats, base_airport) are already documented with examples and bounds; baseline 3 applies. The description restates the filter set but adds no format or syntax 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 (search/list) and resource (aircraft listed on Owner Connect) and enumerates the filter dimensions in the same breath. It also distinguishes itself from the sibling get_aircraft by framing this as the owner-approved listing view versus the public record.

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 to get_aircraft when the public record is wanted, which is a real alternative-selection cue. It lacks an explicit statement of when NOT to use this tool (e.g., when searching unlisted aircraft), so it stops short of full when/when-not 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 only declare readOnlyHint=false/openWorldHint=true/destructiveHint=false, but the description adds substantial behavior: nothing is offered or agreed, the buyer receives an email link, the message is delivered only after confirmation (double opt-in), and the representative replies directly. It also discloses the conditional needs_answers round-trip, which is 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?

Four sentences, purpose front-loaded, each carrying distinct information (purpose, precondition, delivery mechanics, qualification flow). Slightly dense but nothing is wasted; no filler or repetition of the 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 compensates by explaining the only meaningful return path (first call returns needs_answers with the owner's questions) and the confirmation-link delivery flow. It is close to complete for this tool, though it does not say what a normal (non-qualified) successful call returns.

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 already 100%, so baseline is 3, but the description adds real meaning beyond the schema: it ties name/email/message to the person being helped, and crucially explains that 'answers' must be supplied in the order the tool returned the questions on a second call. That sequencing rule is not obvious from the schema item description alone.

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: it 'passes a would-be buyer's message about acquiring one aircraft to the acquisition representative its owner named.' This is clearly distinguishable from siblings like get_aircraft, search_aircraft, estimate_charter, check_availability and request_trip, which cover other lifecycle steps.

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 an explicit precondition: 'Call it only after the person you are helping has asked to contact the owner, with their own name, email and message,' and explains the two-call sequence when qualification questions exist. It does not name an alternative sibling tool or restate when not to reach for this one, so it falls short of a full 5.

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