Motif & Moi

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

Annotations only say readOnly=false, idempotent=false, non-destructive; the description adds the crucial behavioral fact that this call commits nothing commercially and merely produces a prefilled link with a 90-day lifetime. It also discloses the return payload (link, aperçu, devis). It doesn't say what happens on repeated calls (no idempotency guidance) or any quota/auth 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?

Three tight sentences: what is stored, what is returned, and what does NOT happen. The most important caveat (rien n'est commandé) is front and center, and no sentence is filler.

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

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

For a 14-parameter nested tool with no output schema, the description covers the essential facts: outputs are named and the non-committing nature is made explicit. Minor gaps remain around the shipping/postal_code and front_format pricing implications, which the agent must get from the schema alone.

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 already 86%, so almost every parameter is self-documenting. The description adds little beyond restating the main input families (logo URL/base64, textes, prénoms/numéros par pièce, quantités) and the pieces-vs-sizes exclusivity that the schema already states.

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

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

The description states a specific verb (enregistre la personnalisation) and resource (vêtement personnalisé) and names the concrete outputs: a prefilled configurator link, a preview and a quote. This separates it cleanly from siblings like get_design_preview or get_quote, which only read what this tool produces.

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 workflow is spelled out: nothing is ordered, the customer opens the link, checks the visual (bon à tirer), then orders and pays; the link is valid 90 days. What's missing is explicit routing – it never names get_design_preview, get_quote or create_group_order as the next/alternative step, so the agent must infer the sequencing from sibling names.

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 cover the safety profile (write, non-idempotent, open-world). The description adds real behavior: two links are produced with different permissions, members pay online when pay_mode=members, the owner verifies the visual and settles the balance at deadline, and volume pricing retroactively refunds early registrants. Auth requirements and what the response payload contains are still 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 purpose and audience, then the two links in order of importance. Four dense sentences, all relevant; the closing pricing sentence is the least essential for an invocation decision but still informs the choice of 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 14-parameter creation tool with no output schema, the description correctly tells the agent what is returned (a model plus two link URLs, one shared one private). What's missing is who can call it / what account context is required and what happens on deadline expiry — minor against 93% schema coverage.

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

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

Schema coverage is already 93%, so the baseline is 3. The description goes beyond it by explaining the functional consequence of pay_mode=members (each member pays their share online) and per_piece (no static text, each piece varies), which the schema only states mechanically.

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 — creates the group-order model plus two distinct links (members link and owner link) — and names the audience: club, class, association. This is clearly distinguishable from siblings like create_design (single design) or get_group_status (read-only tracking).

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 audience line plus the two-link explanation make the 'when' obvious: multi-person orders needing per-member sizes/names/numbers and split payment. It does not explicitly name alternatives (e.g. 'for a single piece use create_design') or prerequisites, so it stops short of the 5 bar.

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

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds substantive value beyond that by disclosing the shape of the result (PNG, every face marked, plus close-ups), which is important because no output schema exists. It does not mention permissions or whether the preview is cached/expires, 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?

A single efficient sentence that front-loads the output type before the intent. The trailing clause about the client link is slightly cryptic (does the preview become unavailable after the link opens?) but overall there is no waste.

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

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

For a one-parameter read tool with no output schema, the description supplies the essential missing piece – what the return looks like. The only real gap is the meaning of design_id, which leaves it just short of 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?

There is one required parameter, design_id, with 0% schema description coverage, and the description says nothing about it – no format, where to obtain it, or whether it is a design ID vs an order ID. With no annotation of field meaning anywhere, the description should have compensated and does not.

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 (the personalized garment) and a specific output (a PNG image with each marked side and close-ups), so the agent knows exactly what will be produced. It is easily distinguished from the sibling tools (create_design, get_order_status, list_products), though the verb is nominal rather than an explicit 'get/render'.

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 a concrete usage context: showing the render to the client before they open the link. That is a clear 'when to use', but there are no explicit exclusions or named alternatives among the siblings.

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

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

Annotations already declare readOnly, idempotent, non-destructive behavior. The description adds real context beyond them: access is restricted to the owner via owner_key, and the response exposes personal and payment data (names, phone numbers, payments), which is material for handling and privacy. It does not cover pagination or return 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?

A single front-loaded sentence that names the returned data first and the prerequisites last, with no wasted clauses. The parenthetical field list is dense but still 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?

For a read-only lookup with no output schema and zero schema descriptions, it covers the data exposed and the authorization requirement, which is the key gap. It remains silent on result structure, whether all registrations are returned, and pagination or size limits, so an agent knows the gist but not the full contract.

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 0%, so the description must compensate. It helpfully states that both parameters are returned by create_group_order, giving provenance, but it does not explain the role or sensitivity of owner_key as an access credential beyond the ownership hint, nor any format expectations.

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 clearly states the resource — the registrations of a group order (sizes, first names, phone numbers, payments) — and scopes it to the responsible owner. It does not use an explicit verb and only implicitly distinguishes itself from the sibling get_order_status, which handles individual orders.

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 implies usage after create_group_order by pointing to where group_id and owner_key come from, and indicates the caller must be the order's manager. It never states when not to use it or how it relates to get_order_status, leaving the when-to-use vs alternatives 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 establish readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description still adds real context beyond them: the order must be paid, and the caller must supply the email used for payment, which functions as an identity/verification requirement. It does not say what happens for unpaid or not-found orders.

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 with the key qualifier ('commande payée') and both parameter hints front-loaded. No filler, though the phrasing is slightly dense and could separate the verification constraint from the format example.

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

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

With no output schema and no parameter descriptions, the description should say more about the returned stage representation (text status, codes, timestamps) and error behavior on mismatch of email or unpaid orders. For a simple read-only lookup it is adequate but leaves 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 0%, so the description carries the full burden. It documents both parameters meaningfully: order_number carries the MM-XXXXXX format, and email is specifically the address used to pay, implying a must-match constraint. It stops short of stating case sensitivity or format validation rules.

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 and outcome: the manufacturing and delivery stage of a paid order, retrieved via order number and payer email. It is clearly distinguishable from create_design or list_products, but it never explicitly contrasts with get_group_status, the closest sibling for the group-order variant.

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: the phrase 'commande payée' signals this applies to individual paid orders, which implicitly excludes quotes, designs, and group orders. No explicit when-to-use statement or routing to get_group_status for the group case is given.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description reinforces this with 'sans rien enregistrer' and adds value by disclosing what is bundled into the price (quantity discount included, shipping fees, delivery estimate), which annotations cannot convey.

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

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

Two short sentences, no filler, with the output content front-loaded and the single actionable hint (postal_code) placed last. Every 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?

For an 11-parameter nested tool with no output schema, the description does state the shape of the result (price, shipping, estimated date), which is the main missing piece. It does not address the texts/pieces interaction or defaults, but the schema documents those thoroughly at 91% coverage.

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 91%, so the schema already documents category, postal_code, sizes, pieces, texts and the rest. The description only adds the conditional link 'postal_code → delivery date', which the schema property description also states, so it adds little beyond the structured fields.

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 precisely what is computed and returned: exact TTC price including quantity discount, shipping fees, and estimated delivery date for a customization, plus the key qualifier 'sans rien enregistrer'. That implicitly separates it from the create_* siblings, but no sibling is named explicitly, so it stops 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?

The only guidance is the conditional 'Donner postal_code pour la date', which tells the agent how to unlock the delivery estimate but not when to prefer this tool over create_design, create_group_order or list_products. Use context (e.g. quote before ordering) 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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds substantive behavioral context the annotations cannot: that prices are "dès" TTC (starting-from, tax-inclusive), that printable faces carry a max size and a surcharge, and that quantity discounts apply — all decision-relevant for downstream quoting.

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 dense but front-loaded sentence that leads with the resource and stacks attributes efficiently; the ordering directive sits at the end, which is slightly suboptimal placement for the single most actionable instruction.

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

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

With no output schema and only one optional parameter, the description fully carries the burden of describing return content — and it does, itemizing every field family a caller would need before choosing a product or computing a quote.

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 single parameter has 100% schema description coverage ("Filtrer sur une catégorie"), so the baseline is 3. The description implicitly supplies the category vocabulary (T-shirt, sweat, hoodie, polo, tote bag) but never states that `category` filters on those values, so it does not materially exceed 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 enumerates exactly what the resource contains (garment types, qualities, materials, prices, colors, sizes, printable faces, quantity discounts, inks, fonts), so an agent knows this returns the full product catalogue. It never states an explicit verb ("liste" / "renvoie") and does not name sibling tools, but the content is specific enough to distinguish it from create_design or get_quote.

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

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

"À appeler en premier" gives an explicit ordering rule that tells the agent to invoke this before the design/quote/order tools. There is no when-not guidance or named alternative, which is minor for a discovery entry point that has no true substitute.

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