RFQdecoder

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

Annotations only cover readOnly/destructive/openWorld, so the description's disclosure that the compute path is free while the database-reference path costs 1 credit is genuinely additive behavioral context, as is the dual-mode (compute vs read) design. Return shape and any limits on calling it are not described, 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 sentences, front-loaded with the trigger condition, then the behavior, then the exclusion. Each sentence carries distinct information with no padding.

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 2-parameter tool with nested optional inputs and no output schema, the description covers the main decision (compute from user values vs read a reference rate) and the cost model. What is returned (a computed rate value) is left implicit, which is a minor gap given the lack of an output schema.

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

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

Schema coverage is 100%, so the enum and nested machine fields are already fully documented in the schema, establishing the baseline of 3. The description loosely names the value categories (price, utilisation, labour, energy), but this is a partial re-statement rather than added syntax or semantics beyond the schema.

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

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

The description names a specific verb (computes/reads) and resource (machine or workstation hourly rate), with concrete machine examples (CNC, laser, press, welding cell) that anchor the scope. It also carves out a non-overlapping case ('labour-only salary questions'), making it easy to distinguish from siblings like chiffrer_piece or comparer_quantites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a clear triggering condition ('Use this when the user asks for the hourly rate of a machine or workstation') and one explicit exclusion ('Do not use for labour-only salary questions'). It stops short of naming a sibling alternative to route to instead, but the when/when-not context is unambiguous.

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

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description usefully discloses the cost of the call ('1 credit') plus the fact that the response enumerates what is not included. It stops short of explaining that the call is billable/non-read-only in the annotation's terms, or describing latency or failure modes.

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

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

Four sentences, front-loaded with the usage condition and then the return shape, with no filler. The 'ask the user if they are missing' clause is the only slightly procedural addition, but it earns its place for a tool with required inputs.

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

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

With no output schema, the description compensates well by enumerating the returned cost breakdown line by line. It leaves the tuning parameter (ajustements) and the lot/campaign parameters semantically thin, but an agent has enough to select and invoke the tool correctly.

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

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

Schema coverage is 71%, so the schema already documents most parameters (including examples for matiere and the plan_id origin). The description only reinforces that material and quantity are required and should be asked for if absent; it says nothing about ajustements, lot_de_fabrication, nb_campagnes, or epaisseur_mm beyond what the schema carries.

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 (estimate what a manufactured part should cost) plus a concrete output shape (material, operations, setups, overheads, margin). It never names a sibling tool, and the phrase 'quote check' overlaps with verifier_devis, so the differentiation is implicit 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?

It states the triggering situations (should-cost, target price, quote check), the precondition (a plan_id is available), and an explicit exclusion ('Do not use for general price questions without a drawing'). It also tells the agent what to do when inputs are missing: ask the user for material and quantity.

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=false, destructiveHint=false, and openWorldHint=false, which is somewhat surprising for a pure costing computation and is left unexplained. The description adds genuinely non-structured context: the return shape ('one costed line per quantity') and the billing model ('1 credit per quantity'), which an agent needs to avoid runaway cost. It does not clarify why the operation is flagged non-read-only.

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 use case, then the exclusion, then the cost. Every clause earns its place and none is redundant with structured fields.

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?

Covers selection, output nature, and cost, but for an 8-parameter tool with nested objects (ajustements, lot_de_fabrication), no output schema, and a non-read-only annotation, the description leaves the mutation/authorization semantics and the nested parameter behavior unexplained.

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 75%, so the schema carries most parameter meaning and the baseline is 3. The description adds only the quantity range and illustrative values (50, 500, 5000) on top of the schema's minItems/maxItems, and says nothing about matiere, plan_id, ajustements, or lot_de_fabrication.

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 ('see how the unit price of the same part changes with quantity') and scopes it precisely (2 to 8 quantities). It explicitly distinguishes itself from the sibling chiffrer_piece for the single-quantity case, so an agent can route correctly without opening either 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 explicit when-to-use (comparing unit price across quantities), when-not ('Do not use for a single quantity'), and names the alternative (chiffrer_piece). Nothing about tool selection is left to inference.

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 "Free, read-only" is redundant. What does add value is the disclosure of the payload — remaining credits, quotas and recent calls — which is otherwise absent because there is no output schema.

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

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

Two short sentences, front-loaded with the trigger and followed by the return contents. The only wasted clause is "Free, read-only," which restates the annotations rather than earning 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?

For a zero-parameter, no-output-schema read tool, the description supplies the trigger condition and the shape of the result, which is the information an agent would otherwise lack. Nothing material is omitted, though a pointer to the top-up sibling would round it out.

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, so per the baseline there is nothing for the description to disambiguate. No parameter-level information is missing or misleading.

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

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

States a specific verb and resource: it returns remaining credits, quotas and recent calls. That is enough for an agent to know exactly what it gets back. It does not, however, distinguish itself from the obvious sibling recharger_credits (top-up), which it never names.

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?

"Use this when the user asks how many estimates or credits remain, or what limits apply" gives explicit trigger conditions rather than leaving usage implied. It stops short of naming the alternative to reach for instead (recharger_credits) or stating any exclusion, so it is clear context without routing.

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

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the agent already knows this creates local state without destroying anything. The description adds genuinely useful operational context the annotations lack: accepted formats, a 20 MB ceiling, base64 payload encoding, the returned plan_id, and that the call is Free (relevant given the credit-oriented siblings).

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 with zero filler, ordered as use-case, mechanism/return, then exclusion, with the cost signal ('Free.') packed into a single word. Every sentence carries distinct information.

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

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

With no output schema, the description compensates by naming the return payload (plan_id, dimensions, features). Combined with formats, size limit, exclusions, and cost, an agent has everything needed to invoke it correctly without further lookup.

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

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

Schema coverage is 100%, so both parameters are already documented and 3 would be the baseline. The description still adds meaning beyond the schema: which file formats contenu_base64 may carry and the 20 MB size limit, which are constraints neither the schema nor its French examples convey.

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?

Specific verb+resource: uploads a technical drawing of a manufactured part and returns a plan_id plus parsed dimensions and features. The accepted formats (PDF, DXF, STEP) and the costing intent distinguish it from siblings like chiffrer_piece and verifier_devis, which operate downstream on the resulting plan.

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?

Explicit trigger ('when the user provides a technical drawing ... that will be costed') and explicit exclusions ('Do not use for photos, invoices or documents that are not part drawings'). It stops short of naming a specific sibling as the alternative path, so it is clear context rather than full when/when-not/alternatives routing.

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

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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description adds the important behavioral fact that no payment occurs in-conversation, that credits are provisioned only after external payment confirmation, and that invoking the tool itself is free. That is real context beyond the annotations, though it says nothing about failure/abandonment handling.

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

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

Four sentences, all front-loaded with the usage condition first and the return value and pricing following. It is a touch redundant, repeating the pack/price table that the enum schema already carries, which keeps it from 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?

There is no output schema, and the description compensates by explaining exactly what is returned (a Stripe payment page for the user) and when credits take effect. Combined with the usage triggers and pricing, an agent has everything needed to select and call it correctly.

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

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

Schema description coverage is 100% and the single enum parameter already documents all three packs with prices, so the description's pack list largely restates structured data. It adds only the English pack names and the VAT-exclusive phrasing, which is marginal value; 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 names a specific action (buy/top up credits) and states the concrete artifact produced: a secure Stripe card payment page to hand to the user. The sibling tools (chiffrer_piece, calculer_taux_horaire, verifier_devis, etc.) are all estimation/verification tools, so this billing tool is clearly distinguishable by purpose alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit trigger conditions with a restrictive 'only when': the user asks to buy/top up, or an estimate failed for lack of credits and the user wants to continue. That is a clear when-to-use rule that no sibling covers, and no inference is left to the agent.

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

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

Annotations declare readOnlyHint=false, and the description explains why: '1 credit' is consumed per call, which is meaningful cost/disclosure context. It also discloses a real operational limit (scanned PDFs cannot be read, ask the user for the unit price) and that price/quantity/supplier are auto-extracted and returned in devis_lu. Error modes and refund behavior remain unstated.

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

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

Front-loaded with the when-to-use clause, then the operation, then cost, then the input alternatives. Four sentences, all serving a purpose, though the final sentence on the PDF path is dense and could be tightened.

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

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

There is no output schema, yet the description indicates what comes back (line-by-line comparison, supplier questions, devis_lu extraction), covering the main return expectations. Given the nested devis object and 8 parameters, it could say more about the model-tuning parameters, but nothing essential for a correct call is missing.

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

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

With 75% schema coverage the baseline is 3, but the description adds real clarity on the awkwardly expressed devis object: the quote may be passed as prix_unitaire_eur or pdf_base64, and the precedence rule when both are given. It also names plan_id as required, though it omits that matiere and quantite are also mandatory and says nothing about ajustements, epaisseur_mm, nb_campagnes or lot_de_fabrication.

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 ('check a supplier quote') and clarifies the exact operation: comparing the quoted price against the price rebuilt from the drawing, line by line, then listing questions for the supplier. This clearly separates it from sibling pricing tools like chiffrer_piece, which compute rather than verify a price.

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?

Opens with an explicit trigger: 'Use this when the user has a supplier quote for a part and wants to know if the price is fair.' That gives a clear context for invocation. It stops short of naming alternatives or stating when not to use it (e.g., when no drawing/plan exists), so it falls just below the 5 level.

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