Skip to main content
Glama
silamir

boondmanager-mcp-server

by silamir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Préparation de la facturation mensuelle

boond_workflow_preparation_facturation
Read-onlyIdempotent

Generate a billing preparation runbook for a given month: list validated timesheets, ongoing services, orders, amounts still to invoice, issued invoices, and blocking issues (missing or unvalidated timesheets).

Instructions

Pour un mois : CRA validés, prestations en cours et commandes concernées, reste à facturer par commande, factures déjà émises — et la liste de ce qui bloque (CRA manquants ou non validés).

Quand : pour dérouler ce scénario multi-étapes sans avoir à retrouver soi-même le bon enchaînement d'outils et les bons noms de filtres. Plutôt que : le prompt MCP preparation_facturation si le client l'expose — contenu identique, sans consommer un appel d'outil. Cette variante existe pour les clients qui traitent mal prompts/get (claude.ai notamment).

  • N'appelle aucune API BoondManager et ne lit aucune donnée : la réponse est générée côté serveur MCP.

Returns : un runbook en texte — la liste ordonnée des appels Boond à effectuer, avec les filtres exacts. C'est ensuite au modèle de les exécuter ; rien n'est fait par cet appel.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
moisNoMois à facturer : `YYYY-MM`, « ce mois », « mois dernier », « avril 2026 »… Défaut : le mois en cours.
manager_idNoManager pour restreindre à son équipe (les projets de ses N-1). Accepte soit l'ID numérique, soit « Prénom Nom » (le serveur résoudra automatiquement via `boond_resources_search`). Si absent, scope = mon équipe via `perimeterDynamic: ['managers']`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.17.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description specifies that the tool makes no BoondManager API call, reads no data, and generates its answer server-side. It also clarifies the exact division of labor: this call only produces the runbook and the model executes the calls afterward.

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

Conciseness4/5

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

The description is structured with labeled sections ('Quand', 'Plutôt que', 'Returns') and front-loads the output content. It is slightly redundant: the last line repeats the 'rien n'est fait' point already made in the bullet above, but overall every section earns its place.

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

Completeness5/5

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 specifying the return type (text runbook), its content (ordered calls, exact filters, blockers), and its intended follow-up (model executes). Combined with the stated when-to-use and no-side-effect behavior, an agent has everything needed to invoke it correctly.

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

Parameters3/5

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

Schema coverage is 100% and both `mois` and `manager_id` are fully documented in the input schema, so the description carries no additional parameter-level semantics. The first line 'Pour un mois' loosely relates to `mois` but adds no format or default details over the schema.

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

Purpose5/5

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

The definition states a concrete deliverable: a text runbook listing the ordered Boond calls with exact filters for monthly invoicing. It differentiates from the `preparation_facturation` MCP prompt as an alternative, and its 'calls no Boond API and reads no data' clause separates it from all data-access sibling tools.

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

Usage Guidelines5/5

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

A dedicated 'Quand' section tells the agent to use it for multi-step invoicing scenarios when it needs the correct tool sequence and filter names. A 'Plutôt que' section explicitly names the MCP prompt `preparation_facturation` as the preferred choice when the client supports `prompts/get`, and explains this variant is for clients like claude.ai that handle prompts/get poorly.

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

Deploy Server

Other Tools