Skip to main content
Glama
fauguste

boondmanager-mcp-server

Rechercher des validations

boond_validations_search
Read-onlyIdempotent

List pending approvals for absences, expense reports, and timesheets in BoondManager over a month range. Filter by type or state to identify items needing managerial validation.

Instructions

Recherche des validations en attente dans BoondManager (absences, notes de frais, feuilles de temps...).

Quand : pour lister ce qui attend une validation managériale sur une plage de mois. Plutôt que : boond_absences_search, boond_expenses_search ou boond_timesheets_search pour les documents eux-mêmes : celui-ci renvoie l'en-cours de validation, pas leur contenu.

⚠️ startMonth et endMonth (YYYY-MM) sont requis par l'API.

Args:

  • startMonth (string, requis): YYYY-MM (ex: '2025-01')

  • endMonth (string, requis): YYYY-MM

  • documentTypes (string[], optional): 'absencesReport' | 'timesReport' | 'expensesReport'

  • validationStates (string[], optional): 'waitingForValidation' | 'validated' | 'rejected'

  • resourceTypes (number[], optional)

  • keywords (string, optional): préfixes 'TPS', 'EXP', 'ABS', 'COMP'

Returns: Liste des validations correspondantes.

  • fields : projection côté MCP, jamais transmise à l'API — remplace le résumé par les seuls attributs listés (noms inconnus ignorés). À utiliser sur les grosses pages.

  • Pagination : pageSize 1–500 (défaut 30), page 1–100 — au-delà : refus, affiner les filtres.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoNuméro de page (max: 100)
fieldsNoProjection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.
endMonthYesMois de fin YYYY-MM. Requis.
keywordsNoMots-clés. Préfixes acceptés : 'TPS' (CRA), 'EXP' (frais), 'ABS' (absence), 'COMP' (ressource).
pageSizeNoNombre de résultats par page (max: 500, défaut: 30)
startMonthYesMois de début YYYY-MM. Requis.
documentTypesNoTypes de documents à valider.
resourceTypesNoIDs de types de ressource (dictionnaire setting.typeOf.resource).
validationAlertsNoFiltrer sur les validations avec alertes.
validationStatesNoÉtats de validation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.12.2
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. Changed1 schema field changedv2.9.0
    • addedInput schema / properties / fields
      Added value: +{
      +  "description": "Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  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?

The annotations already cover read-only/idempotent/non-destructive behavior. The description adds valuable non-obvious behavioral details: startMonth/endMonth are API-required, fields is a client-side MCP projection never sent to the API, unknown field names are ignored, and pagination is hard-limited with refusal beyond page 100/pageSize 500. 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.

Conciseness5/5

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

The structure is effective: purpose, when to use, alternatives, required args, return type, then behavioral caveats. Though longer than minimal, the 10-parameter surface justifies the length, and each sentence adds value without filler.

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 search tool with no output schema, this is complete enough for correct invocation: required months, filter enums, keywords, resourceTypes, projection behavior, and pagination limits are all covered. The annotations carry the safety profile, and the description covers the remaining operational constraints.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds meaningful extras beyond the schema: a concrete date format example, the MCP-side behavior of fields, and the pagination refusal behavior. Most enum and type information restates the schema, so 4 rather than 5.

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 clearly states the operation ('Recherche des validations en attente') and the resource (validations in BoondManager), with concrete document types. It explicitly differentiates itself from boond_absences_search, boond_expenses_search, and boond_timesheets_search by clarifying that it returns the validation workflow, not document content.

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?

It provides an explicit 'Quand' condition: list what awaits managerial validation over a month range. It also provides a 'Plutôt que' section naming the sibling tools to avoid and the reason, giving an agent clear selection 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