Factures impayées à relancer

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

Annotations already declare read-only, idempotent, non-destructive. The description adds valuable context: it does not call any BoondManager API and does not read any data, with the response generated server-side. It also clarifies that nothing is executed by this call—only a runbook is returned. This goes well beyond the annotations and gives the agent a precise understanding of side effects and security.

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 structured with clear sections (purpose, when to use, alternative, behavior, returns). It is somewhat lengthy but each part adds value, and the most important purpose is front-loaded. The only slight inefficiency is the repetitive mention of the runbook concept, but overall it's well-organized.

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 workflow tool with a single optional parameter and no output schema, the description fully explains the output (a runbook with exact filters), the internal behavior (no API calls), and the usage context. It also provides an alternative path. An agent has everything needed to decide whether to call it and what to expect.

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% for the single parameter. The description adds meaning: society_id accepts either a numeric ID or a comany name, with automatic resolution via `boond_companies_search`. This clarifies the input format and resolution behavior, which is helpful for correct invocation, exceeding the baseline.

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 the tool lists unpaid invoices with past due date, grouped by company, and optionally filtered by company. However, the initial sentence 'Liste les factures impayées' could be misread as returning actual data, while later it clarifies the tool returns a runbook (ordered instructions) rather than the data itself. This nuance is eventually clear but initially slightly ambiguous. It is distinct from sibling workflow tools because of its specific scenario.

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?

Explicitly states when to use it ('pour dérouler ce scénario multi-étapes sans avoir à retrouver soi-même le bon enchaînement d'outils et les bons noms de filtres') and directly names an alternative (the MCP prompt `factures_a_relancer`), explaining the trade-off (avoids an API call but only for clients that handle prompts/get poorly). This leaves no doubt about selection.

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