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.