Skip to main content
Glama
silamir

boondmanager-mcp-server

by silamir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Récupérer un dictionnaire BoondManager

boond_application_dictionary
Read-onlyIdempotent

Fetch BoondManager dictionary data by dot-path to translate state/type IDs into readable labels before filtering.

Instructions

Récupère un dictionnaire de référence BoondManager (états, types, pays, devises, langues, outils, expertises, ...).

Quand : pour traduire un état ou un type BoondManager entre son ID entier et son libellé, avant de filtrer une recherche. Plutôt que : les ressources boond://dictionary/* pour les tables courantes (états, typeOf, pays, devises, langues) : même contenu par un resources/read, sans consommer un appel d'outil. Cet outil reste nécessaire pour les tables non publiées en ressource.

L'API expose un seul endpoint /application/dictionary qui renvoie tout — le serveur le cache (TTL 1h, configurable via BOOND_DICTIONARY_TTL_MS) et extrait un sous-arbre par chemin dotté.

Chemins usuels de dictionaryType (relatifs à data) : - "setting.state.{resource,candidate,contact,company,opportunity,project,invoice,order,positioning}" → états par entité - "setting.typeOf.{resource,contact,project}" → types par entité - "setting.action.{candidate,resource,opportunity,project,...}" → actions disponibles - "setting.tool" → outils / technos (Java, AWS...) - "setting.expertiseArea" → domaines d'expertise - "setting.experience" → niveaux d'expérience - "setting.languageSpoken" → langues parlées - "setting.activityArea" → secteurs d'activité - "setting.mobilityArea" → mobilités géographiques - "setting.currency" → devises - "setting.civility" → civilités - "country" → pays - "languages" → langues d'interface (fr, en, es)

Note : l'ancienne forme "states/resources" (slash) n'est pas valide — utilisez "setting.state.resource".

Returns : le sous-arbre demandé (souvent un tableau {id, value, …}), ou isError: true avec le chemin fautif s'il est introuvable.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dictionaryTypeYesChemin dotté relatif à `data` de /application/dictionary (ex: setting.state.resource, setting.typeOf.project, setting.action.candidate, setting.tool, country, languages). La forme « states/resources » (slash) n'est pas valide.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.17.0
    • changedInput schema / properties / dictionaryType / description
      Previous value: -"Type de dictionnaire (ex: typeOf/actions, typeOf/absences, states/candidates, states/resources, states/opportunities, states/projects, states/invoices, countries, currencies, languages...)"New value: +"Chemin dotté relatif à `data` de /application/dictionary (ex: setting.state.resource, setting.typeOf.project, setting.action.candidate, setting.tool, country, languages). La forme « states/resources » (slash) n'est pas valide."
  2. Changed1 schema field changedv2.12.2
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. First observedv2.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds substantial context beyond that: the single API endpoint behavior, server-side caching with TTL 1h configurable via BOOND_DICTIONARY_TTL_MS, sub-tree extraction by dotted path, isError: true with faulty path on miss, and the invalid legacy 'states/resources' slash form. 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 long but logically structured with clear section headers (Quand, Plutôt que, API behavior, Chemins usuels, Returns) and is front-loaded with the core purpose. The common-paths list is arguably the most actionable content for an agent. Minor deduction for length, but 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?

Complete for this tool: no output schema exists, so the description explains the return format ('souvent un tableau {id, value, …}, ou isError: true'). With 1 well-documented parameter, clear annotations, and coverage of purpose, usage, behavior, paths, and errors, nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100% for the single parameter dictionaryType, which is already well documented with examples and the slash-form caveat. The description goes further with a 'Chemins usuels' list enumerating ~15 concrete paths (setting.state.resource, setting.tool, country, languages, etc.), giving agents far more than the schema alone.

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 opens with a specific verb+resource: 'Récupère un dictionnaire de référence BoondManager (états, types, pays, devises, langues, outils, expertises, ...)'. It clearly states what the tool retrieves and lists concrete dictionary categories. None of the ~200 sibling tools perform dictionary lookups, so it is easily distinguished.

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?

Has an explicit 'Quand' section stating when to use it (to translate a BoondManager state/type between integer ID and label before filtering a search) and a 'Plutôt que' section naming the alternative: boond://dictionary/* resources for common tables, with the condition that those suffice and only non-published tables require this tool. This is exemplary when/when-not/alternatives 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