Skip to main content
Glama
silamir

boondmanager-mcp-server

by silamir
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Rechercher des notes de frais

boond_expenses_search
Read-onlyIdempotent

Search expense reports in BoondManager filtered by resource, project, and period to find matching records and avoid duplicate submissions before creation.

Instructions

Recherche des notes de frais dans BoondManager avec filtres par ressource, projet et période.

Quand : avant toute création : l'API ne déduplique pas, deux notes de frais peuvent coexister sur le même couple (ressource, mois). Plutôt que : boond_expenses_get pour le détail des lignes d'une note de frais identifiée.

resourceId / projectId sont convertis en références keywords (COMP / PRJ) : l'API n'a pas de paramètre dédié.

Returns: Liste des notes de frais correspondantes.

  • fields : projection côté MCP, jamais transmise à l'API — remplace le résumé par les seuls attributs/relations 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 (défaut: 1, max: 100)
fieldsNoProjection : attributs ou relations (type#id) par résultat (ex: ['title','dependsOn']). Absent = résumé standard. Noms inconnus ignorés.
endDateNoDate de fin (YYYY-MM-DD)
keywordsNoMots-clés de recherche
pageSizeNoNombre de résultats par page (max: 500, défaut: 30)
projectIdNoFiltrer par ID projet (référence keywords PRJ<id>)
startDateNoDate de début (YYYY-MM-DD)
resourceIdNoFiltrer par ID ressource (référence keywords COMP<id>)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNombre d'éléments retournés sur cette page
itemsYes
totalNoNombre total de résultats côté BoondManager

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.18.0
    • changedInput schema / properties / fields / description
      Previous value: -"Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés."New value: +"Projection : attributs ou relations (type#id) par résultat (ex: ['title','dependsOn']). Absent = résumé standard. Noms inconnus ignorés."
  2. Changed6 schema fields changedv2.17.0
    • changedInput schema / properties / page / description
      Previous value: -"Numéro de page (max: 100)"New value: +"Numéro de page (défaut: 1, max: 100)"
    • changedInput schema / properties / pageSize / description
      Previous value: -"Résultats par page"New value: +"Nombre de résultats par page (max: 500, défaut: 30)"
    • changedInput schema / properties / projectId / description
      Previous value: -"Filtrer par ID projet"New value: +"Filtrer par ID projet (référence keywords PRJ<id>)"
    • addedInput schema / properties / projectId / pattern
      Added value: +"^\\d+$"
    • changedInput schema / properties / resourceId / description
      Previous value: -"Filtrer par ID ressource"New value: +"Filtrer par ID ressource (référence keywords COMP<id>)"
    • addedInput schema / properties / resourceId / pattern
      Added value: +"^\\d+$"
  3. Changed2 schema fields changedv2.12.2
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • removedOutput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  4. Changed1 schema field changedv2.9.0
    • addedInput schema / properties / fields
      Added value: +{
+  "description": "Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  5. Changed1 schema field changedv2.7.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "count": {
+      "description": "Nombre d'éléments retournés sur cette page",
+      "type": "number"
+    },
+    "items": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "attributes": {
+            "additionalProperties": {},
+            "description": "Attributs projetés (présent si `fields` est fourni)",
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          },
+          "id": {
+            "type": "string"
+          },
+          "summary": {
+            "description": "Résumé standard (absent si `fields` est fourni)",
+            "type": "string"
+          },
+          "type": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "description": "Nombre total de résultats côté BoondManager",
+      "type": "number"
+    }
+  },
+  "required": [
+    "count",
+    "items"
+  ],
+  "type": "object"
+}
  6. 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 cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the API's lack of deduplication, the internal resourceId/projectId → keywords (COMP<id>/PRJ<id>) translation that has no API-side equivalent, the out-of-range pagination refusal, and that `fields` is an MCP-side projection never transmitted to the API. These are non-obvious traits an agent would otherwise misjudge.

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?

Front-loaded with the core purpose, then segmented into 'Quand', 'Plutôt que', 'Returns' and two bullets for projection and pagination. Dense but every line carries actionable information; no filler sentences.

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?

An output schema exists so return values need not be detailed, yet a brief 'Returns' line is still given. Filtering, projection, and pagination constraints are all covered, and the workflow routing to the sibling get tool closes the loop for a mutation-adjacent read tool.

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, but the description adds real meaning beyond the schema: that `fields` is applied MCP-side and replaces the summary (useful on large pages), and that exceeding pageSize/page bounds results in a refusal rather than clamping. The COMP/PRJ keyword rewrite partly duplicates the schema's own wording, which keeps this from a 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?

States a specific verb ('Recherche') and resource ('notes de frais') plus the filterable dimensions (ressource, projet, période), which an agent can map directly to the resourceId/projectId/date params. It also names the sibling boond_expenses_get as the detail-oriented alternative, so the search-vs-get split is unambiguous.

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?

Explicit 'Quand' clause ties usage to a concrete workflow moment (before any creation, because the API does not deduplicate and two expenses can coexist for the same resource/month) and an explicit 'Plutôt que' clause routing the agent to boond_expenses_get. Both when-to-use and when-to-use-something-else are present.

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