Skip to main content
Glama
silamir

boondmanager-mcp-server

by silamir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Ingérer un e-mail ou un compte rendu dans le CRM

boond_workflow_ingest_communication
Read-onlyIdempotent

Extract contacts, companies, and commitments from pasted emails or meeting notes, then create or link BoondManager records after validation.

Instructions

À partir d'un e-mail, d'un compte rendu d'appel ou d'une note de réunion collés dans la conversation : extrait les entités (contact, société, engagements), déduplique contre BoondManager, présente le plan d'écriture, puis crée ou rattache contact / société / action après validation explicite. Aucun Sampling : c'est le modèle qui extrait.

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 ingest_communication 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
contenuNoLe texte brut (e-mail, CR d'appel, note). Absent → prendre ce qui a été collé dans la conversation.
type_actionNoNature de l'action à tracer : appel, email, rendez-vous, note… Défaut : déduite du texte.
opportunite_idNoOpportunité à laquelle rattacher l'action. Accepte soit l'ID numérique, soit l'intitulé de l'opportunité (résolution auto via `boond_opportunities_search`).

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?

The description clearly discloses that the tool makes no BoondManager API calls, reads no data, and performs no action itself — it only generates a runbook server-side. This adds crucial context beyond the annotations (readOnlyHint, idempotentHint, destructiveHint) and clarifies that the 'creates or attaches' wording refers to future model-executed steps, not this call. No contradiction with annotations.

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 well-structured with clear sections (process, Quand, Plutôt que, bullet, Returns) and front-loaded with the core behavior. It is somewhat long (~180 words) for a tool description, but nearly every sentence earns its place by clarifying usage, behavior, or return format.

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?

For a complex workflow tool, the description covers the entire agent-visible lifecycle: input source, extraction logic, deduplication, write-plan generation, the explicit distinction that this call does nothing, and the expected return format (ordered list of Boond calls with filters). An agent knows exactly what to do after invoking it.

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?

Input schema coverage is 100%, so the schema already fully documents all three parameters. The description reinforces that `contenu` can be omitted (pasted content), but adds no new semantic detail about `type_action` or `opportunite_id` beyond what the schema provides. Baseline 3 is appropriate.

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 description states a specific verb (ingérer) and resource (e-mail/compte rendu/note), and outlines the full process: extraction, deduplication, write plan, and creation/attachment after validation. It also distinguishes itself from the MCP prompt alternative (`ingest_communication`) and from the many sibling workflow tools by naming the exact scenario it covers.

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?

The 'Quand' section explicitly says when to use it (multi-step scenario without needing to find the tool chain/filters), and the 'Plutôt que' section names the alternative (the MCP prompt `ingest_communication`) and when to prefer this tool (clients that handle `prompts/get` poorly, e.g., claude.ai). This is direct, specific guidance.

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