Créer un regroupement de prestations

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

Annotations already declare non-readOnly, non-idempotent, non-destructive. The description adds value by warning that the body is derived from 'models.groupment' and is 'non éprouvé sur un tenant de test' (untested on a test tenant), which is a crucial caveat. It also specifies the return format. This exceeds the annotation baseline, though it doesn't describe potential side effects beyond creation, which is implied by non-idempotency.

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 well-structured with clear sections: purpose, when-to-use, alternatives, warnings, and returns. It is concise, with no wasted words, and the key purpose is front-loaded. Bullet points and line breaks improve readability. Every sentence contributes essential 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?

Given the tool's complexity (11 params, but many optional), the high schema coverage, existing output schema (mentioned as 'structuredContent.id'), and annotations, the description covers purpose, usage, alternatives, a risk warning, and return format. It is complete enough for an agent to invoke correctly without needing additional information.

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 each parameter already has a description. The description mentions the body is derived from 'models.groupment' (title, dates, prices, relations), which gives a high-level overview but adds no new meaning beyond the schema. It doesn't clarify relationships between parameters or provide usage examples. Baseline 3 is appropriate given complete schema 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 clearly states the tool's purpose: grouping multiple project services under a single price and period for combined invoicing. It specifies the verb 'Regroupe', the resource 'prestations d'un projet', and the context 'pour les facturer ensemble'. It also distinguishes itself from siblings by explicitly mentioning 'boond_groupments_default' and 'boond_groupments_update'.

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 explicit usage guidance: 'Quand : pour la facturation multi-prestations' and alternatives: 'Plutôt que : `boond_groupments_default` d'abord ; `boond_groupments_update` pour ajuster un regroupement existant.' This tells the agent exactly when to use this tool versus the alternatives.

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