Skip to main content
Glama
fauguste

boondmanager-mcp-server

by fauguste
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Rechercher des achats/sous-traitance

boond_purchases_search
Read-onlyIdempotent

Search purchase orders and subcontracting commitments in BoondManager. Filter by keywords, company, or project to track spending commitments before invoices arrive.

Instructions

Recherche des achats et sous-traitances dans BoondManager.

Quand : pour suivre les engagements de dépense et la sous-traitance. Plutôt que : boond_provider_invoices_search pour les factures effectivement reçues : l'achat est l'engagement, la facture fournisseur le document qui le solde.

Args:

  • keywords, companyId, projectId: Filtres

  • page, pageSize: Pagination

Returns: Liste des achats correspondants.

  • 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.

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.
keywordsNoMots-clés de recherche
pageSizeNoRésultats par page
companyIdNoFiltrer par ID société
projectIdNoFiltrer par ID projet

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

A4.1/5.0
Behavior4/5

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

Annotations already include readOnlyHint=true and destructiveHint=false, indicating a safe read operation. The description adds value by explaining the fields parameter is a MCP-side projection that is never sent to the API, and that unknown field names are ignored. This goes beyond annotations by clarifying internal behavior, though it doesn't detail other behavioral aspects like pagination limits or response structure.

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 concise with clear sections ('Quand', 'Plutôt que', 'Args', 'Returns', and a note on `fields`). It front-loads the purpose and usage, and the paragraphs are efficient without excessive verbosity. Minor redundancy in the args list but overall well-structured.

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

Completeness4/5

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 and annotations covering safety, the description is fairly complete. It covers purpose, usage context, and parameter roles alphabetically. It lacks explicit details on response structure (e.g., summary format) but this may not be necessary given the tool's simplicity. The `fields` parameter behavior is explained, which is useful.

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%, so the schema already documents all parameters including defaults and constraints. The description lists 'keywords, companyId, projectId: Filtres' and 'page, pageSize: Pagination', which adds a light grouping but doesn't elaborate on syntax or meaning beyond the schema. This is baseline 3, as the description provides minimal extra value.

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

Purpose4/5

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

The description clearly states it searches for purchases and subcontracting ('achats et sous-traitances') in BoondManager, with a specific verb ('Recherche') and resource. It distinguishes itself from a sibling tool by noting the difference between purchase orders and provider invoices. However, it could be more explicit about its exact scope relative to other search 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?

The 'Quand' section explicitly states when to use this tool (to track spending commitments and subcontracting) and contrasts it with `boond_provider_invoices_search` for received invoices, clarifying the purchase is the commitment and the invoice is the settlement document. This provides clear usage guidance and alternative selection.

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