boondmanager-mcp-server

Rechercher des livraisons / CRA

boond_deliveries_search

Read-onlyIdempotent

Find deliveries in BoondManager by filtering on project, company, resource, state, period, and perimeter. Returns matching service lines.

Instructions

Recherche des prestations / livraisons dans BoondManager par projet, société, ressource, état (deliveryStates, projectStates), période (period: "running" + dates pour les prestations en cours) et périmètre (perimeter*).

Quand : pour retrouver des prestations (lignes de mission facturables) sur un périmètre. Plutôt que : boond_projects_deliveries_groupments quand on part d'un projet connu — plus direct.

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

Returns: Liste des livraisons 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

Name	Required	Description
`page`	No	Numéro de page (défaut: 1, max: 100)
`sort`	No	Champ de tri (ex: lastName, firstName, updateDate)
`flags`	No	IDs de drapeaux (flags) — `boond_flags_search`.
`order`	No	Ordre de tri (asc/desc)
`fields`	No	Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.
`period`	No	Champ de date borné par `startDate` / `endDate` : started, stopped, updated, running (prestations en cours sur la fenêtre), projectRunning (projet en cours).
`endDate`	No	Date de fin (YYYY-MM-DD), à utiliser avec `period`.
`keywords`	No	Mots-clés de recherche
`pageSize`	No	Nombre de résultats par page (max: 500, défaut: 30)
`companies`	No	IDs de sociétés (filtre API natif, équivalent de `companyId` pour plusieurs sociétés).
`companyId`	No	Filtrer par ID société (référence keywords CSOC<id>)
`projectId`	No	Filtrer par ID projet (référence keywords PRJ<id>)
`startDate`	No	Date de début (YYYY-MM-DD), à utiliser avec `period`.
`resourceId`	No	Filtrer par ID ressource (référence keywords COMP<id>)
`projectTypes`	No	IDs de types de projet — `boond://dictionary/typeOf/projects`.
`transferType`	No	Filtre sur les transferts de prestation (master / slave / none / notSlave / notMaster / missing).
`opportunityId`	No	Filtrer par ID opportunité (référence keywords AO<id>)
`periodDynamic`	No	Fenêtre relative appliquée à `period` (à la place de `startDate` / `endDate`) : today, thisWeek, thisMonth, lastMonth, thisYear, untilToday…
`projectStates`	No	IDs d'états de projet — `boond://dictionary/states/projects`.
`deliveryStates`	No	IDs d'états de prestation — `boond://dictionary/states/deliveries`.
`expertiseAreas`	No	Domaines d'expertise — `boond://dictionary/expertiseAreas`.
`perimeterPoles`	No	IDs de pôles. Conserve les entités dont le responsable appartient à ces pôles.
`narrowPerimeter`	No	Si true, jointure ET entre les filtres `perimeter*` (au lieu de OU par défaut).
`perimeterDynamic`	No	Périmètre dynamique relatif à l'utilisateur courant (raccourci sans avoir à connaître son propre ID). Valeurs : 'data' (mes propres données), 'managers' (mon équipe / mes N-1), 'agencies' (mes agences), 'poles' (mes pôles), 'businessUnits' (mes BU). Combinable.
`perimeterAgencies`	No	IDs d'agences. Conserve les entités dont le responsable appartient à ces agences.
`perimeterManagers`	No	IDs des managers (ressources). Conserve les entités dont le responsable est l'un de ces managers. Pour 'mon équipe / N-1 d'une personne X', passer [X_id]. Obtenir son propre ID via boond_application_current_user.
`perimeterBusinessUnits`	No	IDs de business units. Conserve les entités dont le responsable appartient à ces BU.

Output Schema

TableJSON Schema

Name	Required	Description
`count`	Yes	Nombre d'éléments retournés sur cette page
`items`	Yes
`total`	No	Nombre total de résultats côté BoondManager

Schema Changelog

Changes observed during successful MCP inspections.

Changed30 schema fields changedv2.17.0Sep 26, 2026

addedInput schema / properties / companies

Added value: +{
+  "description": "IDs de sociétés (filtre API natif, équivalent de `companyId` pour plusieurs sociétés).",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

changedInput schema / properties / companyId / description

Previous value: -"Filtrer par ID société"New value: +"Filtrer par ID société (référence keywords CSOC<id>)"

addedInput schema / properties / companyId / pattern
```
Added value: +"^\\d+$"
```

addedInput schema / properties / deliveryStates

Added value: +{
+  "description": "IDs d'états de prestation — `boond://dictionary/states/deliveries`.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

changedInput schema / properties / endDate / description

Previous value: -"Date de fin (YYYY-MM-DD)"New value: +"Date de fin (YYYY-MM-DD), à utiliser avec `period`."

addedInput schema / properties / endDate / pattern
```
Added value: +"^\\d{4}-\\d{2}-\\d{2}$"
```

addedInput schema / properties / expertiseAreas

Added value: +{
+  "description": "Domaines d'expertise — `boond://dictionary/expertiseAreas`.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / flags

Added value: +{
+  "description": "IDs de drapeaux (flags) — `boond_flags_search`.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / narrowPerimeter

Added value: +{
+  "description": "Si true, jointure ET entre les filtres `perimeter*` (au lieu de OU par défaut).",
+  "type": "boolean"
+}

addedInput schema / properties / opportunityId

Added value: +{
+  "description": "Filtrer par ID opportunité (référence keywords AO<id>)",
+  "pattern": "^\\d+$",
+  "type": "string"
+}

addedInput schema / properties / order

Added value: +{
+  "description": "Ordre de tri (asc/desc)",
+  "enum": [
+    "asc",
+    "desc"
+  ],
+  "type": "string"
+}

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)"

addedInput schema / properties / perimeterAgencies

Added value: +{
+  "description": "IDs d'agences. Conserve les entités dont le responsable appartient à ces agences.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / perimeterBusinessUnits

Added value: +{
+  "description": "IDs de business units. Conserve les entités dont le responsable appartient à ces BU.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / perimeterDynamic

Added value: +{
+  "description": "Périmètre dynamique relatif à l'utilisateur courant (raccourci sans avoir à connaître son propre ID). Valeurs : 'data' (mes propres données), 'managers' (mon équipe / mes N-1), 'agencies' (mes agences), 'poles' (mes pôles), 'businessUnits' (mes BU). Combinable.",
+  "items": {
+    "enum": [
+      "data",
+      "agencies",
+      "poles",
+      "businessUnits",
+      "managers"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / perimeterManagers

Added value: +{
+  "description": "IDs des managers (ressources). Conserve les entités dont le responsable est l'un de ces managers. Pour 'mon équipe / N-1 d'une personne X', passer [X_id]. Obtenir son propre ID via boond_application_current_user.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / perimeterPoles

Added value: +{
+  "description": "IDs de pôles. Conserve les entités dont le responsable appartient à ces pôles.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / period

Added value: +{
+  "description": "Champ de date borné par `startDate` / `endDate` : started, stopped, updated, running (prestations en cours sur la fenêtre), projectRunning (projet en cours).",
+  "enum": [
+    "started",
+    "updated",
+    "stopped",
+    "projectRunning",
+    "running",
+    "hasAdditionalDataOrPurchase"
+  ],
+  "type": "string"
+}

addedInput schema / properties / periodDynamic

Added value: +{
+  "description": "Fenêtre relative appliquée à `period` (à la place de `startDate` / `endDate`) : today, thisWeek, thisMonth, lastMonth, thisYear, untilToday…",
+  "enum": [
+    "today",
+    "yesterday",
+    "tomorrow",
+    "thisWeek",
+    "lastWeek",
+    "nextWeek",
+    "thisMonth",
+    "lastMonth",
+    "nextMonth",
+    "thisTrimester",
+    "lastTrimester",
+    "nextTrimester",
+    "thisSemester",
+    "lastSemester",
+    "nextSemester",
+    "thisYear",
+    "lastYear",
+    "nextYear",
+    "thisFiscalYear",
+    "lastFiscalYear",
+    "nextFiscalYear",
+    "untilToday"
+  ],
+  "type": "string"
+}

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+$"
```

addedInput schema / properties / projectStates

Added value: +{
+  "description": "IDs d'états de projet — `boond://dictionary/states/projects`.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / projectTypes

Added value: +{
+  "description": "IDs de types de projet — `boond://dictionary/typeOf/projects`.",
+  "items": {
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  "type": "array"
+}

addedInput schema / properties / resourceId

Added value: +{
+  "description": "Filtrer par ID ressource (référence keywords COMP<id>)",
+  "pattern": "^\\d+$",
+  "type": "string"
+}

addedInput schema / properties / sort

Added value: +{
+  "description": "Champ de tri (ex: lastName, firstName, updateDate)",
+  "type": "string"
+}

changedInput schema / properties / startDate / description

Previous value: -"Date de début (YYYY-MM-DD)"New value: +"Date de début (YYYY-MM-DD), à utiliser avec `period`."

addedInput schema / properties / startDate / pattern
```
Added value: +"^\\d{4}-\\d{2}-\\d{2}$"
```

addedInput schema / properties / transferType

Added value: +{
+  "description": "Filtre sur les transferts de prestation (master / slave / none / notSlave / notMaster / missing).",
+  "enum": [
+    "master",
+    "slave",
+    "none",
+    "notSlave",
+    "notMaster",
+    "missing"
+  ],
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "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"
+}

Changed1 schema field changedv2.12.2Aug 14, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```

Changed1 schema field changedv2.9.0Aug 3, 2026

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"
+}

First observedv2.1.0May 30, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds significant behavioral context: `projectId`/`companyId` are converted to keyword references (PRJ<id>/CSOC<id>) because the API has no dedicated parameter, the `fields` projection is MCP-side and never sent to the API, and pagination limits (pageSize 1–500, page 1–100) with refusal beyond. These are non-obvious API behaviors that an agent must know to call the tool correctly, far exceeding what annotations cover.

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 description is well-structured: a concise opening sentence stating purpose and filters, followed by 'Quand' and 'Plutôt que' guidance, then two bulleted technical notes. It is front-loaded with the most essential information, and every sentence carries unique value – no schema repetition or filler. Length is appropriate for the tool's complexity (27 parameters).

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?

Given the tool's complexity (27 parameters, many enums, perimeter logic), the description is remarkably complete. It covers usage context, sibling differentiation, ID conversion, projection behavior, pagination constraints, and a brief note on `period`. The output schema already handles return structure, so no need to explain returns. All information an agent needs to call this correctly is present or inferred from schema/annotations.

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% with each parameter described, so the baseline is 3. However, the description enhances semantics for key parameters: it explains the keyword conversion for `projectId`/`companyId`, the MCP-side nature of `fields`, and the pagination bounds for `pageSize`/`page`. These add meaning not present in the schema, justifying a score above baseline, though the majority of parameters rely on the schema descriptions.

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 verb 'Recherche' (search) and the resource 'prestations / livraisons', and enumerates the main filters (project, company, resource, state, period, perimeter). It also explicitly differentiates from the sibling `boond_projects_deliveries_groupments`, telling the agent when to prefer the other tool. This makes the purpose unambiguous and distinct.

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 description includes a dedicated 'Quand' (when) section stating the tool is for finding billable deliverable lines on a perimeter, and a 'Plutôt que' (instead of) section directing the agent to `boond_projects_deliveries_groupments` when starting from a known project. This gives explicit usage conditions and alternative routing, fully satisfying the dimension.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server