VTC AEROPORT PARIS

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: prices are TTC and in euros, and the result is a per-vehicle price rather than a single quote, which partially compensates for the absent 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?

Three short sentences, front-loaded with what the tool returns then when to call it then a pricing caveat. Every sentence carries distinct information with no repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only pricing tool with no output schema, the description conveys the return shape (price per vehicle), the units (TTC euros), and the workflow position. Remaining gaps such as error behavior for unserviceable addresses or whether quotes expire are minor.

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% with rich per-parameter descriptions (address format, enum meaning, heure de Paris ISO 8601, maxItems). The description only echoes date and trip-type concepts at a high level and adds no syntax or constraint detail beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Donne le prix fixe de chaque vehicule') plus the scope (trajet ou mise a disposition, a une date donnee), which is exactly the distinction between the two modes it supports. It also implicitly separates itself from the booking sibling by instructing to call it before any reservation.

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?

'A appeler avant toute reservation' gives clear temporal context for when this tool belongs in the workflow. It does not name a specific alternative or state when-not to use it, so it stops short of full routing guidance.

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

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false). The description adds genuinely useful context beyond them: this is a lookup on an existing reservation and requires both the booking number and the email used to make it, effectively disclosing an identity-verification requirement. It stops short of describing the returned shape.

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 short sentences, nothing wasted, with the core action front-loaded ahead of the input requirements.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only lookup with annotations covering safety and no output schema, the description supplies what an agent needs: what it returns and which two identifiers are required. Return structure is not described but is not strictly required here.

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?

With schema description coverage at 0% and two required parameters, the description compensates well by naming and explaining both: 'le numero de reservation' (booking number) and 'l e-mail du client utilise pour la reservation'. It adds meaning the bare schema does not provide, though no format/type detail is given.

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: it returns the status of an already-made reservation ('Donne l etat d une reservation deja faite'). The phrase 'deja faite' implicitly separates it from the sibling 'reserver', but no sibling is named 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?

Usage is only implied: consult it to check the state of an existing booking, requiring the booking number and customer email. There is no explicit when-to-use/when-not guidance nor mention of alternatives such as 'reserver' or 'calculer_prix'.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile (safe, static, closed-world read) is covered. The description adds a modest amount of value by naming the returned attributes (capacity, equipment), but says nothing about caching, rate limits, or data freshness that would go beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single efficient sentence that front-loads the resource and then the returned fields. No filler, though it is a bare minimum rather than a model of structure.

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 parameters and no output schema, the description meaningfully compensates by stating what the list contains (vehicle ranges plus passenger/baggage capacity and equipment). It is complete enough to invoke correctly, missing only guidance on when to prefer it over its siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, which is the baseline-4 case; the empty schema is consistent with a simple catalog listing. There is nothing parameter-wise for the description to clarify.

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 ('Liste') and resource ('gammes de vehicules de VTC AEROPORT PARIS') and even previews the returned content (capacity, equipment). It is clearly distinguishable from siblings like calculer_prix or reserver, though it never explicitly contrasts itself with 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?

The description offers no when-to-use guidance, no prerequisites, and does not mention any alternative sibling (e.g. calculer_prix for pricing rather than fleet browsing). The agent must infer usage from the tool 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?

Annotations already declare the mutation profile (readOnly=false, destructive=true, idempotent=false, openWorld=true), so the bar is lower. The description adds two genuinely useful facts beyond them: the mandatory client-approval gate and that the price is recalculated server-side (so the final price may differ from the quote). It still does not say what happens on failure, whether a booking can be duplicated, or how confirmation is signalled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action, then the precondition, then the price caveat. Nothing is redundant and no sentence could be dropped without losing meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter mutation with nested objects and no output schema, the description covers the invocation gate well but says almost nothing about the return (other than the price being recalculated), nor about failure or refund/cancel paths. The payment-mode outcomes (payment link for en_ligne) live only in the schema, so the high-level behaviour described is thinner than the tool's complexity warrants.

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 77% and the schema documents the enums, formats, and nested client object thoroughly, so the structured data does the heavy lifting. The description only reinforces the accord_client precondition already stated in the schema. Per the coverage rule, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

« Enregistre la reservation pour le client » states a specific verb (enregistrer) and resource (reservation), and the reference to calculer_prix identifies the sibling this tool depends on versus the read-side lire_reservation / lister_vehicules. An agent can tell what this tool does and where it sits in the 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?

The description gives an explicit gating rule: call ONLY after calculer_prix and after the client's explicit approval of the recap. That is a concrete when-to-use ordering constraint with a hard precondition (accord_client), not an implied one. The only gap is that it doesn't name alternatives to use instead, but the prerequisite already rules them 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?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety/open-world profile is covered. The description adds that it works from a partial input and returns candidate complete addresses, but says nothing about result count, ranking, or geographic scope.

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 compact sentence with the core action front-loaded and no filler. Nothing is redundant, though it could be marginally 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?

For a single-parameter, read-only, open-world lookup with no output schema, the description plus annotations give an agent enough to call it correctly. The only gap is any detail about the shape/number of suggestions returned.

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 single parameter is fully documented in the schema ('Debut d adresse, nom d hotel, de gare ou d aeroport'). The description only restates that it is a partial input, adding no new meaning 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 (propose/suggests) and resource (complete addresses) with the scope of input (a partial entry). It is clearly distinct from the sibling tools (calculer_prix, reserver, lister_vehicules), though it never names or contrasts them 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?

The clause 'pour confirmer l adresse exacte avec le client' implies the usage context (resolving/confirming an address during a booking flow), but there is no explicit when-to-use, when-not, or reference to an alternative tool.

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