GEO360 Concierge

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

With no annotations provided, the description carries the full disclosure burden. Beyond the verb 'Publishes' it says nothing about whether the RFQ is durable, cancellable, or how 'atomic bilateral clearing' actually behaves — a critical gap for a marketplace-mutating call.

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 the action front-loaded and no filler. The second sentence is dense with undefined terminology rather than redundant, so it earns its place but could be clearer.

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, 5-required mutation with no annotations and no output schema, the description is only minimally adequate. It omits the relationship to the geo360_b2a_* feasibility tools it references and to the geo360_acommerce_settle counterpart that follows an RFQ.

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 92%, so the schema already documents nearly all 12 parameters, which sets the baseline at 3. The phrase 'Links to Phase 1 feasibility contexts' loosely gestures at the optional *_id parameters (route_risk_id, customs_gate_id, price_context_id) but adds no new syntax or format detail.

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 — 'Publishes a ... Request For Quote (RFQ)' — which is enough to separate it from settle, book_offer, and hold_offer siblings. However, qualifiers like 'sovereign' and 'atomic bilateral clearing' are jargon that don't sharpen the operational meaning for an agent.

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 guidance is given at all. The description never explains how an RFQ differs from the sibling actions geo360_book_offer or geo360_hold_offer, nor what prerequisite state (e.g. an existing feasibility context) must exist before publishing.

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 behavioral burden, and it does disclose two useful non-obvious traits: a 75 bps clearing fee is captured and an arbitration contract is established as a side effect. However, it omits whether settlement is irreversible, what permissions or identity verification are required, and what happens on failure or double-submission.

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 the action front-loaded and the financial/legal consequence in the second. Domain jargon ('bilateral clearinghouse', 'arbitration contract') is dense but each clause 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?

This is a 7-parameter financial settlement mutation with no annotations and no output schema, yet the description gives no lifecycle context: no return value expectation, no confirmation of irreversibility, no indication of what the arbitration contract implies for the caller. For a high-stakes settlement tool, this is under-specified.

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 one of the 7 parameters is already documented in the schema, and the description adds no parameter-level detail beyond it. Baseline 3 is appropriate when the schema does the heavy lifting.

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 pair (clears and settles) and resource (autonomous wholesale transaction via bilateral clearinghouse), which is materially more informative than the opaque tool name. It is distinguishable from the geo360_acommerce_rfq sibling, though the description never names that sibling or states the relationship between them.

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 explicit when-to-use/when-not guidance and no stated prerequisites such as requiring a prior accepted RFQ or a matching clearing hash. The phrase 'via bilateral clearinghouse' hints at the context, but the agent must infer from the required rfq_id parameter that this is the post-RFQ settlement step.

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 behavioral burden, and it falls short: it never states whether this is a read-only search or a mutating/booking call, nor does it mention permissions, rate limits, pagination, or what 'verified broker links' implies about the response. The phrase 'verified broker links' gestures at output content but without enough specificity to be actionable.

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?

It is a single front-loaded sentence with no filler, which is structurally efficient. However, cramming four vehicle types plus two tour regions plus a broker-links claim into one verb-less phrase leaves it descriptive but un-actionable.

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 5-parameter tool with no annotations and no output schema, the description is too thin: it omits the search-vs-book distinction, says nothing about session_id chaining or sub_id attribution that the schema implies, and gives no routing guidance among the many sibling tools.

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 60%, leaving parameters like duration_days and vehicle_type partially unexplained, and the description adds no parameter meaning of its own. Its vehicle list even conflicts with the enum by naming scooters, which is not an accepted value, actively muddying the parameter semantics.

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 resource category (bikes, motorcycles, scooters, campervans for active touring) but supplies no verb — it is a noun phrase, so an agent cannot tell whether it searches, books, or lists inventory. It also fails to distinguish itself from the sibling geo360_search_car_rentals, and the mention of 'scooters' does not match the enum (campervan, bicycle, motorcycle, ebike).

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 guidance, no prerequisites, and no mention of the obvious alternative geo360_search_car_rentals or the booking siblings (geo360_hold_offer, geo360_book_offer) that would follow a search. The agent must infer the role of this tool entirely from the name.

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?

No annotations are provided, so the description carries the full behavioral burden. 'Gatekeeper' hints that the result may block or flag a shipment, but the description never says whether it is read-only, whether it mutates state, what happens on failure, or what the verdict looks like — significant gaps for a 7-parameter compliance tool with no annotation coverage.

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 sentence that front-loads the phase, role, and the four regulatory regimes it covers. The acronyms are expanded inline (CBAM), though 'PHASE 1 B2A' is internal jargon that costs the reader without adding routing value.

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 7 parameters, no annotations, and no output schema, the description must explain what the tool returns and how it is used downstream. It does not: an agent cannot tell whether the output is a pass/fail gate, a liability estimate, or a checklist, nor how a failed gate should affect the workflow.

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 71%, near the threshold where the schema does most of the work, and the required hs_code/origin_country are documented in-schema with examples. The description adds no parameter-level detail, though mentioning CBAM carbon liability loosely signals the declared_embedded_emissions_tco2e_per_t input.

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 role (regulatory gatekeeper) and enumerates the concrete regimes it checks: customs import compliance, EU CBAM carbon liability, EUDR deforestation rules, and a certificate checklist. That is more than a restatement of the name, though it never explicitly distinguishes itself from the other B2A tools (b2a_price_context, b2a_route_risk) or states what the agent gets back.

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 'PHASE 1 B2A' prefix weakly implies this runs before later phases, but there is no statement of when to call it, what prerequisite inputs must exist, or which sibling tool handles the adjacent steps. No exclusions or alternatives are named.

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 usefully discloses 'strict quote TTL' and that settlement is out of scope, but says nothing about permissions, idempotency, or the read-only nature beyond implication. Adequate but not rich.

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 front-loaded sentences with the phase tag first, and every sentence carries content (purpose, usage condition, boundary). No filler, though 'PHASE 1 B2A' jargon is not self-explanatory.

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?

No output schema and no annotations, so the description should do more to describe the returned 'structured price context' (fields, TTL semantics). It covers purpose and a boundary but leaves the return shape and failure behavior unspecified.

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 7 parameters are already documented in the schema. The description adds no parameter-level meaning (nor syntax for material_spec or TTL relationship), 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 structured price context for critical commodities and raw materials') with the benchmark style (LME/Platts) called out. It does not name a specific sibling, though 'before publishing an RFQ tender' loosely ties it to the RFQ tool.

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?

Provides clear context for when to invoke it ('Evaluates price awareness before publishing an RFQ tender') and a hard boundary ('Does not execute trade settlement'). It stops short of explicitly naming the alternative tool to use for settlement, so no full when/when-not/alternative triad.

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?

No annotations are provided, so the description carries the entire behavioral burden. It characterizes the assessment's analytical content but says nothing about safety profile, whether it is read-only or mutating, authentication requirements, rate limits, or the meaning of the session_id-based state coordination. That is a substantial gap for an unannotated 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?

A single front-loaded sentence that leads with the domain ('PHASE 1 B2A') and the core action. Efficient, though the cryptic phase/prefix consumes the opening position without conveying meaning to the agent.

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 helpfully outlines the return content (risk factors, chokepoint status, delay probabilities), which is the strongest part of the definition. But for a 7-parameter tool with zero annotations it omits routing guidance and any behavioral caveats, leaving the definition only minimally 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 description coverage is 71%, so the parameters (corridors, transit_mode enum, hazardous_material, session_id) are largely self-documenting and the baseline is 3. The description enumerates what the analysis covers rather than clarifying any input, so it adds little to 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 verb and resource: 'Assesses supply chain freight corridor risks' with a concrete scope (chokepoints, bunker fuel index, transit delay probabilities). The action is distinguishable from the many non-risk siblings, though the 'PHASE 1 B2A' prefix is opaque jargon and it never contrasts itself with near-neighbors like geo360_b2a_customs_gate or geo360_b2a_price_context.

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 explicit when-to-use instruction, no prerequisites, and no reference to any alternative tool. In a 25-tool catalog with three other 'b2a' siblings, the absence of routing guidance leaves the agent to infer selection from the name alone.

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 and does well: it discloses the PCI posture (no card PANs, opaque payment_ref/consent token), the success outputs (order_id / voucher references), and a degraded-mode behavior (structured fallback to deep_link when API book is unavailable). It omits reversibility/cancellation, authorization prerequisites, and rate-limit or async-completion behavior, which matter for an 11-parameter booking mutation.

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 tight sentences, front-loaded with the primary action, then the constraint, then the return/fallback behavior. No filler; 'PHASE 2/3 (API)' is the only mildly internal jargon and it still conveys placement.

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 zero-required, 11-parameter mutation with no annotations and no output schema, the description covers the essentials an agent needs: the two booking paths, the payment-safety constraint, and what comes back on success or fallback. It leaves roughly half the parameters (locale, currency, sub_id, agent_ref, session_id, idempotency_key) unexplained, which is the main remaining gap.

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 55%, and the description's parameter information (hold_id preferred over offer_id, payment_ref/consent token semantics) largely restates what the schema already says for those fields. It adds no meaning for the undocumented parameters (locale, sub_id, currency, agent_ref, session_id, idempotency_key), so it neither compensates for the gap nor goes 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 verb and resource ('Confirms a booking against a hold_id ... or directly against offer_id'), which cleanly separates it from the sibling geo360_hold_offer by making the hold-vs-book relationship explicit. The 'PHASE 2/3 (API)' prefix adds lifecycle positioning, so an agent can place this tool in a multi-step flow without opening the 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 a clear preferred path ('hold_id (preferred)') and a conditional alternative ('offer_id if partner allows'), which is real selection guidance. It does not name a when-not condition or point at any sibling tool as the alternative for the non-booking case, so it stops short of full 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?

With no annotations, the description carries the full behavioral burden, and it does add real context: the claim goes through third-party 'vetted legal recovery partners' and is capped at 600 EUR. However, it omits mutation-critical facts such as whether the submission is irrevocable, what personal data is shared with partners, idempotency, and what happens for ineligible flights.

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 dense sentence that front-loads the action and legal basis and closes with the monetary outcome. Nothing is redundant, though the run-on structure packs eligibility, compensation cap and partner mechanism together without separation.

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 six-parameter, one-required mutation tool with no annotations and no output schema, the description is adequate on purpose but silent on outcomes — it does not say whether a claim reference, partner redirect, or estimate is returned, nor how flight_number alone is sufficient to validate a claim.

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 including defaults and examples (IB3166, BA456) are already documented in the schema. The description adds no parameter-level detail beyond that, 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?

Names a specific verb ('Submits') and a specific resource ('EU261 / UK261 air passenger rights claims') and scopes the eligible disruption types (delayed, cancelled, overbooked). No sibling tool covers flight-delay compensation, so an agent can route here unambiguously.

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 disruption categories imply the triggering situation, but there is no explicit when-to-use/when-not statement, no eligibility prerequisites (passenger must actually have been on the flight, claim window, jurisdiction), and no alternative tool named. Usage is inferable rather than stated.

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?

No annotations are provided, so the description carries the full burden. It mentions 'verified, tracked' and 'attribution' but does not disclose permissions required, side effects (e.g., whether a record is created), error handling for invalid option_id, or rate limits. The behavioral profile is substantially incomplete for a tool with no annotation coverage.

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 description is a single, front-loaded sentence with dense but useful context. 'PHASE 2 HANDOFF' is compact and informative, though the trailing parameter list is slightly crowded, keeping it from a perfect score.

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 should carry more behavioral and return-value context. It adequately identifies the tool's purpose and inputs but leaves gaps about what the generated link looks like, whether it expires, and what happens on failure.

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 baseline is 3. The description reiterates sub_id, agent_ref, locale, and currency but adds no meaning beyond what the schema already documents with examples and detailed descriptions.

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 ('Generates') and resource ('verified, tracked affiliate deep link') with clear scope ('for any option_id returned by GEO360 search tools'). It distinguishes this handoff tool from search and booking siblings by tying its input to search outputs.

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 'PHASE 2 HANDOFF' framing and mention of 'option_id returned by GEO360 search tools' implies this tool should be used after a search, but it does not explicitly state when not to use it or name alternative tools like book_offer or hold_offer. Usage is inferable but not spelled out.

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?

No annotations are provided, so the description carries the full behavioral burden, and it falls short. It hints that the result includes 'affiliate activation deep links' but does not disclose whether the call is read-only or creates a booking, whether it requires a session_id, what authentication is needed, or anything about rate limits or idempotency. These are material unknowns for a commerce-adjacent 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?

It is a single, grammatically tight sentence with no filler, which is good. However, brevity here stems from under-specification rather than discipline: the sentence spends its words on promotional framing ('Instant', 'for travelers', '190+ countries') instead of the operational information an agent needs.

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 five parameters, no output schema, and no annotations, the description should explain what comes back (a link? a list of packages?) and how session_id ties calls together across a trip. It explains none of this, and does not clarify the read-vs-write nature of the operation, leaving the agent under-informed for the tool's apparent complexity.

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 each of the five parameters documented in the schema (including defaults for days/data_gb and the session_id chaining note). The description adds no parameter meaning beyond that, so the baseline of 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?

The description reads as marketing copy ('Instant international eSIM cellular data packages for travelers across 190+ countries') rather than a functional statement. It names a resource domain but never states the action the tool performs — is it a search returning package options, or a purchase that returns an activation link? The verb 'get' in the name suggests retrieval while 'verified affiliate activation deep links' suggests a transaction result, so the agent cannot tell what the call actually 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?

There is no indication of when to call this tool, what preconditions exist, or how it relates to siblings such as geo360_search_flights or geo360_generate_affiliate_link. A 190+ country scope is stated but no selection criteria are given, so usage must be inferred entirely from the name.

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 and does so well: it discloses that price/inventory is locked, that the hold is temporary and TTL-bounded, that no charge occurs, and that unsupported partners yield a structured fallback payload. It omits error/expiry behavior and any auth or rate-limit context, keeping it short of 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 tight sentences with no filler, and the core action is front-loaded before the capability caveat and fallback. The 'PHASE 2 (API)' prefix is context-lite but not wasteful.

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 9-parameter, no-output-schema, annotation-free mutation tool, the description covers the essential behavior: what is locked, that nothing is charged, the partner-capability dependency, and the fallback path. It leaves hold expiry/failure handling unstated, which is a minor remaining gap.

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 78%, so the schema already documents most parameters (offer_id provenance, TTL bounds, quantity, principal_hints non-sensitivity). The description adds only the constraint that offer_id must come from a prior search response, which is already reflected in the schema; no additional semantics beyond the 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 (places a temporary hold), the resource (offer_id from a prior search), and the effect (locks price/inventory for a TTL). It also explicitly differentiates itself from geo360_book_offer by noting it 'Does not charge the principal', so an agent can distinguish it from siblings without reading the 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 an explicit conditional route: use this when the partner supports api_hold, otherwise fall back to geo360_generate_affiliate_link. It does not spell out the relationship to geo360_book_offer (i.e., hold-then-book sequencing) or other when-not cases, so it stops short of full 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?

With no annotations, the description carries the full behavioral burden, and it discloses almost nothing: the word "confidential" implies an encrypted/private channel, but there is no statement about authorization mechanics, whether the handshake creates persistent session state, idempotency, or side effects. For a protocol-style channel-establishment operation, this is a substantial 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?

A single front-loaded sentence with no filler. It is efficient, though the sparseness borders on under-specification rather than true conciseness.

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, no output schema, and a stateful-sounding channel-establishment semantic, one sentence is not enough. The description should say what authorization is required, what the agent gets back, and what state the handshake creates; none of that is present.

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 fully documents principal_hash, client_channel, and flight_trip_id. The description adds no syntax, format, or relationship detail beyond the schema, which is the expected baseline when the schema does 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 verb ("Establishes") and a named resource ("confidential KAM direct channel"), plus the target audience ("authorized B2A client agents"). It is reasonably distinguishable from the other b2a_* siblings, but it never differentiates itself explicitly from them, and what "establishing a channel" operationally means is left to inference.

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 a hint of a precondition ("for authorized ... client agents"), but no when-to-use, when-not-to-use, or alternative tool is named. An agent has no guidance on when this handshake is required versus calling e.g. geo360_b2a_price_context directly.

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 behavioral burden. It usefully discloses a state transition ('transitions consignment status to PHYSICAL_DELIVERY_CONFIRMED') and a validation step on the eIDAS seal, which tells the agent this is a mutation with a pass/fail gate. However, it omits what happens on seal-validation failure, error behavior, idempotency, and permission requirements.

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, front-loaded with the phase tag then the action and its effect. The 'PHASE 3 B2A' prefix is cryptic process metadata but compact, and nothing is wasted.

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?

No output schema and no annotations, so the description must cover behavior, and it does surface the resulting status. For a mutation tool it still leaves gaps around failure modes, auth, and return shape, so an agent would know what it does but not fully how it behaves.

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 are already documented in the schema. The description restates e-CMR and eIDAS seal concepts that map to required params but adds no syntax, format, or defaulting detail beyond the schema; 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?

The description gives a specific verb ('Confirms') and resource ('physical freight receipt at destination hub') and names the resulting state ('PHYSICAL_DELIVERY_CONFIRMED'). It situates the tool in a workflow ('PHASE 3 B2A') but never names the sibling it follows (e.g. geo360_logistics_dispatch_packet), so differentiation is implied rather than 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?

The 'PHASE 3' marker and the reference to e-CMR receipt imply this is called after dispatch, but there is no explicit when-to-use vs. alternatives, no stated preconditions beyond the required seal, and no exclusions. Usage is inferable from the phase label rather than stated.

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?

No annotations are provided, so the description carries the full burden. It hints at behavior by saying 'cryptographically signed,' but never discloses whether this is a write/creation operation, what side effects or artifacts it produces, whether it requires specific authority or contract references, or any rate/irreversibility characteristics for a legal-document generator.

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 no filler or repetition. It is efficient, though its brevity borders on under-specification rather than true conciseness.

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 11-parameter tool with 7 required fields, no annotations, and no output schema that produces signed legal/compliance documents. The description omits return format, authorization needs, and the relationship between required inputs and the generated packet, leaving significant gaps for a high-stakes operation.

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 one of the 11 parameters is already documented in the schema (e.g., contract_ref, rfq_id, sub_id). The description adds no param-level meaning such as which fields map to which document, 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 (generates) and resource (dispatch packets) and enumerates concrete document types (Bill of Lading, e-CMR, ISO compliance), so the agent knows exactly what is produced. It does not, however, differentiate itself from logistics siblings like geo360_logistics_delivery_confirm or the escrow/cosign tools.

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 guidance, no prerequisites, and no mention of alternative tools. Given a sibling set packed with logistics, customs, and escrow operations, the description leaves the agent to infer where dispatch-packet generation fits in the workflow.

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 behavioral burden and mostly fails it. 'Verified booking links' is the one useful behavioral signal, implying the tool returns links rather than completing a booking, but there is no mention of auth requirements, rate limits, whether results are live/available inventory, or what happens on a bad city input. Too thin for a zero-annotation 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?

A single front-loaded sentence with no redundancy, which is structurally sound. But the content is largely marketing copy ('500+ cities', 'secure', 'verified') that does not earn its place over operational detail. Concise but not informative.

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 five-parameter, no-annotation, no-output-schema tool, the description omits essentials: what the response looks like (list of storage points? links? prices?), whether the city_or_station must match a known hub, and how session_id ties into subsequent calls (only the schema hints at this). Inadequate for the tool's complexity.

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 five parameters including the session_id workflow and sub_id attribution. The description adds nothing beyond the schema, which is the expected baseline of 3 when structured fields do the heavy lifting.

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 resource (luggage storage consignas near train stations and airports) and implicitly distinguishes it from siblings like search_flights and search_car_rentals. However, it never states the operation: is this a search that returns locations, or a booking tool? The phrase 'with verified booking links' hints at a discovery/redirect tool, but the agent must infer the verb. Purpose is recognizable but under-specified.

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. The geographic scoping ('near train stations and central airports') is context, not usage guidance. An agent gets no help deciding this tool over, say, get_esim_connectivity or search_car_rentals for a traveler's logistics needs.

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 usefully discloses that it is an affiliate search layer, does not book directly, and returns ranked options with option_id for affiliate deep-links. It omits authentication requirements, rate limits, and pagination behavior.

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 tightly written sentences with no waste. Purpose is front-loaded, followed by return format and key behavioral disclaimer, making it easy to scan and understand.

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 complex tool with 8 parameters, no output schema, and no annotations, the description covers the essential purpose and return type. It could better explain the importance of date parameters or session reuse, but the schema handles most parameter details.

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 88%, so the schema already documents parameters thoroughly. The description adds no parameter-level meaning beyond what is in the schema, which is acceptable given the high coverage.

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 'Metasearches' and resource 'car rentals, campervans, and local vehicle fleets' with clear geographic scope (Europe, North America, alpine corridors). Explicitly distinguishes from booking siblings with 'Does not book directly — acts as affiliate search layer.'

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?

Provides a clear context and an exclusion ('Does not book directly'), which tells the agent this is for search, not booking. However, it does not name a specific alternative tool or state when to choose this over other search tools (e.g., geo360_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?

With no annotations, the description must carry the behavioral burden. It usefully discloses the non-booking nature, that results are ranked, and that option_id feeds affiliate linking. It omits whether calls are rate-limited, whether prices are live/cached, auth requirements, and how long option_ids remain valid before needing a hold.

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 tight sentences, front-loaded with the core purpose before the non-booking caveat. Zero filler and every clause carries signal.

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 8-parameter tool with no output schema and no annotations, the description is thin on return-value shape beyond 'ranked options with option_id' and omits the search-to-book handoff workflow. It is adequate to identify the tool but not fully sufficient to invoke it confidently in a multi-step trip flow.

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 88%, so the schema already documents nearly all eight parameters including session_id threading and the cabin_class enum. The description adds no parameter-level detail (e.g. date formats, session reuse) beyond what the schema provides, 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 ('Metasearch of commercial passenger flights globally') and distinguishes itself from transactional siblings by explicitly saying it does not book directly. An agent can tell it apart from geo360_book_offer and geo360_hold_offer immediately.

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 description implies a search-first workflow by noting option_id is 'ready for affiliate deep-link generation', which gestures at geo360_generate_affiliate_link, and it rules out booking. However, it never explicitly states when to use this versus geo360_book_offer/geo360_hold_offer, nor any prerequisites or session_id continuity 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?

With no annotations, the description carries the full burden, and it does disclose meaningful context: the 2-of-3 threshold scheme, the Swiss Code of Obligations/DLT Act framing, and that its effect is to authorize (not execute) disbursement. But for a cryptographic signing operation it omits critical traits: whether a signature is reversible or irrevocable, idempotency, permission/auth requirements, and failure modes. The gaps are significant for a mutation tool with zero annotation coverage.

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 with no padding, and the core action is front-loaded. The informational prefix 'PHASE 3 B2A' is arguably wasted space, keeping it short of a 5.

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 must stand alone, and while it conveys the legal/threshold context well, it does not tell the agent what a successful or failed co-sign returns, whether the threshold is now met, or what happens on subsequent calls. For a high-stakes signing tool it is adequate but incomplete.

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 including the cosign_role enum and contract_ref provenance are fully documented in the schema. The description adds no parameter-level detail such as the default role behavior or the meaning of proof_delivery_code. Baseline 3 is appropriate when the schema does the heavy lifting.

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 gives a specific verb and resource: executing 2-of-3 multisig co-signing on the escrow vault, plus the downstream purpose of authorizing disbursement. It is distinguishable from geo360_swiss_escrow_deposit and geo360_swiss_escrow_disburse, though it never names those siblings explicitly. The 'PHASE 3 B2A' prefix is internal jargon that adds no clarity.

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 phrase 'satisfies the threshold requirement (signatures 2/3) to authorize disbursement' implies this is called when the second/third signature is needed, giving some usage context. However, there is no explicit when-to-use vs alternatives guidance, no stated prerequisites (e.g., that contract_ref must originate from geo360_acommerce_settle), and no exclusions. Usage must be 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?

With no annotations, the description carries the full behavioral burden and falls well short. For an escrow-initialization operation it never states whether the action is irreversible, what permissions or signatures are needed to call it, whether funds move immediately, or what the resulting contract state is.

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 no waste or redundancy. It is well-sized, though it is arguably too terse for the complexity of the operation rather than 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?

For a financial escrow contract initialization with 8 parameters, no annotations, and no output schema, the description is far too thin. It omits the role of the third (non-buyer/seller) key in the 2-of-3 scheme, prerequisites, and post-initialization state, none of which is recoverable from structured fields.

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 88%, so the schema already documents nearly every parameter (pubkeys, contract_ref, gross_amount_eur, session/sub/settlement IDs). The description adds no field-level meaning beyond that, so the baseline 3 for high coverage 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 clear verb ('Initializes') and a specific resource ('2-of-3 Swiss multi-signature escrow contract'), which is more informative than the bare name. However, it does not differentiate from close siblings like geo360_swiss_escrow_cosign and geo360_swiss_escrow_disburse, so the agent cannot tell which escrow stage this represents without inferring from the name.

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 guidance on when to use this versus geo360_swiss_escrow_cosign, geo360_swiss_escrow_disburse, or geo360_acommerce_settle (which the contract_ref schema references). The 'Swiss Code of Obligations' phrase is legal context, not usage routing, so the agent is left to guess at sequencing.

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 and does disclose key behavior: it is the 'final atomic' step, splits proceeds to a named destination, and routes the 75 bps fee to the sovereign treasury. It still omits whether the action is irreversible or what happens on partial failure, but it is well above the average mutation 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?

Two sentences, front-loaded with the phase and action, well within budget. The trailing 'returns real-time liquidity pool telemetry' is slightly promotional but earns its place by hinting at the response.

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 mutation tool with no annotations and no output schema, the description covers the value movement, fee capture, and a hint of the return payload. It is close to complete, lacking only a statement about reversibility/error behavior.

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 five parameters, including the 2-of-3 authorization condition on contract_ref and the enum rail. The description adds only the fee/proceeds economics, not parameter-level meaning. 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: executing final atomic disbursement of escrowed funds, with the value split (99.25% net to seller, 75 bps to treasury) spelled out. It is distinguishable from siblings like escrow_deposit/escrow_cosign by the word 'final', though it never explicitly names those alternatives.

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 'PHASE 3' label implies this runs only after deposit and cosign, which is useful sequencing context. However, there is no explicit when-to-use statement or exclusion, and no guidance on prerequisites such as confirming the 2-of-3 threshold before calling.

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 a meaningful trait – it submits externally to Villiers operators and demands explicit human confirmation – which hints at a consequential action. But it omits whether this is reversible, whether it books/charges anything, and any side effects or rate limits.

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, front-loaded with the step and action, then prerequisites. No filler or redundancy.

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 unannotated, externally-facing action with no output schema and low parameter coverage, the description covers the essential sequencing and human-confirmation gate but leaves outcomes, side effects, and most parameters undocumented. Adequate but with clear gaps.

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 only 36% and there are 11 parameters, so the description must compensate. It only clarifies estimate_token's provenance ('from Step 1'); origin, destination, departure_date, email, name fields, and the aircraft_category default are left entirely to 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 verb and resource: 'Submits confirmed live charter pricing request to Villiers operators'. The 'STEP 2' framing distinguishes it from the estimate sibling (Step 1), so an agent can tell it apart. It's clear, though what 'confirm' actually commits to (request vs. booking) is left slightly ambiguous.

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 hard prerequisite: a valid estimate_token from Step 1, plus a required 'explicit human confirmation' gate. This effectively routes the agent to geo360_vip_aviation_estimate first. It does not spell out when NOT to use it or how to handle failure/retry, 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?

With no annotations, the description carries the full disclosure burden. It does disclose an unusual output artifact ('cryptographic qualification token'), which is genuinely useful behavioral context, but it says nothing about permissions, cost, rate limits, or how the token is consumed downstream, and never states that this is a non-mutating pricing read.

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 mandatory-step designation first and no padding. The unexplained 'cryptographic qualification token' phrase is jargon that costs a little clarity but is brief.

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 7-parameter, annotation-free tool with no output schema, the description covers purpose, workflow position, and the token artifact, but omits the effects of sandbox, passengers, and round_trip, and does not explain how the qualification token is used. Adequate but with clear gaps.

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 57%, with origin/destination/sub_id/session_id documented in the schema itself. The description adds no parameter meaning of its own and leaves sandbox, passengers, and round_trip undocumented except by their bare names and defaults.

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 ('Indicative private jet charter pricing') and scopes it to four aircraft categories, so an agent can distinguish it from its sibling geo360_vip_aviation_confirm (a confirmation rather than an estimate). It does not explicitly name the sibling it complements, 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?

'MANDATORY STEP 1' implies sequencing (call before confirm), which is useful workflow context, but the description never names the follow-on tool or states when this tool should NOT be used. Usage is implied rather than spelled out.

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 behavioral burden. It implies a read-only search via 'flights' but never confirms it, and says nothing about whether results are bookable, how 'real-time' freshness works, pagination, or auth/affiliate requirements for sub_id.

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 no filler. It is efficient, though it is perhaps too terse for a 5-parameter tool with no 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?

Five optional parameters, no annotations, and no output schema — the description does not compensate by explaining what is returned (a list of empty-leg offers?), whether it is read-only, or how it relates to the booking/hold siblings. Significant gaps remain for an agent to invoke 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 description coverage is 80%, so the schema already documents origin, destination, sub_id, and session_id. The description adds no filtering or format guidance beyond that, and the undocumented 'limit' default is left to the schema. Baseline 3 applies when the schema does the heavy lifting.

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 gives a specific verb-like resource ('empty-leg repositioning flights') with qualifiers ('real-time discounted', 'Villiers private aviation fleet'), so an agent can distinguish this discovery tool from siblings like geo360_vip_aviation_estimate or geo360_search_flights. It does not explicitly name the sibling it is not, 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?

There is no guidance about when to call this versus geo360_search_flights, geo360_vip_aviation_estimate, or the booking tools like geo360_hold_offer/geo360_book_offer. No prerequisites, no conditions, no exclusions are stated.

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?

No annotations are provided, so the description carries the full behavioral burden and falls short. It never states whether this is a read/search or a mutation, what the 'strict coastal verification' actually enforces, or any pricing, availability, or auth implications. Only the vague verification phrase adds anything beyond the name.

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?

It is a single front-loaded sentence with no wasted words, but the brevity stems from under-specification rather than disciplined concision for a 7-parameter tool.

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 7-parameter tool with 43% schema coverage, no annotations, no output schema, and no stated action verb, the description leaves major gaps an agent needs before invoking 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 description coverage is only 43%, so the description must compensate and does not. It references 'motor yacht and catamaran', mapping to just two of the four vessel_category enum values, and says nothing about guests, budget_eur, charter_days, sub_id, or session_id.

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 (luxury motor yacht and catamaran charters) which distinguishes it from the aviation and logistics siblings, but it supplies no verb at all. An agent cannot tell whether this searches, estimates, holds, or books a charter.

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 guidance, no mention of alternatives (e.g. geo360_vip_aviation_estimate, geo360_book_offer), and no exclusions. 'Strict coastal geographic verification' hints at a constraint but never states what qualifies or what happens when it fails.

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 behavioral burden, yet it discloses nothing: no mutation vs read-only, no side effects, no cost, auth, or reversibility info. 'High-ticket' implies expense but gives no operational behavior.

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?

One concise sentence, but it is marketing copy rather than front-loaded operational information. Brevity is not wasted, yet it fails to front-load purpose or action.

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 complex 7-parameter, multi-vertical, high-ticket tool with no output schema and no annotations, the description omits purpose, usage, parameters, and behavior. It is wholly inadequate 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?

Description mentions no parameters. Schema coverage is 57%, leaving stay_days, passengers, and budget_total_eur undocumented in both schema and description. No guidance on session_id, sub_id, or how the multi-vertical combo maps to inputs.

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?

Restates the tool name ('master combo' → 'multi-layer concierge combining ...') with marketing labels but no operational verb. An agent cannot tell whether this books, holds, estimates, or searches, nor how it differs from sibling vip_aviation_estimate or vip_marine_charter.

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, prerequisites, or alternative tools are mentioned. The many sibling vip_* and booking tools are not referenced, leaving the agent to guess whether this supersedes or complements them.

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 behavioral burden, yet it discloses nothing about read-only vs. booking behavior, authentication, rate limits, result volume, or pagination. The only behavioral signal is the implicit trust claim 'verified by Plum Guide,' which is marginal.

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?

It is a single, tight sentence with no filler, which is good for length. But as a marketing fragment it conveys no actionable information, so it is more under-specification than genuine conciseness.

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 5-parameter tool with no output schema, no annotations, and a 60%-documented schema, the definition is far too thin. An agent lacks the guidance needed to choose this tool over its many siblings or to call it correctly, especially around guest capacity and budget semantics.

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 only 60%: guests and budget_eur (both with defaults) have no descriptions, and the description adds no meaning for any of the five parameters, not even the EUR currency unit for budget_eur or the guests count range. It fails to compensate for the documented-parameter 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?

The description identifies the inventory domain (curated architectural sanctuaries, Michelin-grade chalets, historic estates verified by Plum Guide), which lets an agent infer this is a luxury-accommodation search tool distinct from marine-charter or aviation siblings. However, it never states a verb or action, reading as marketing copy rather than a functional definition.

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 guidance, no exclusions, and no mention of alternative tools among the many search/charter siblings (e.g. geo360_vip_marine_charter, geo360_search_car_rentals). The agent must infer that this is the accommodation-search entry point purely from the tool name.

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