boondmanager-mcp-server

Rechercher des demandes d'absence

boond_absences_search

Read-onlyIdempotent

Search absence requests in BoondManager by date range, resource, validation state, and scope.

Instructions

Recherche des demandes d'absence dans BoondManager, par période (startMonth / endMonth en YYYY-MM, requis), ressource, état de validation (validationStates) et périmètre (perimeter*).

Quand : pour retrouver des demandes d'absence et leur état de validation. Plutôt que : boond_planning_absences_search pour la vue calendaire (qui est absent quand), et boond_validations_search pour ce qui reste en attente de validation.

resourceId est converti en référence keywords COMP : l'API n'a pas de paramètre dédié.

Returns: Liste des demandes d'absence 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)
`order`	No	Ordre de tri (asc/desc)
`fields`	No	Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.
`endMonth`	Yes	Mois de fin de période (YYYY-MM) — obligatoire pour l'API
`keywords`	No	Mots-clés de recherche
`pageSize`	No	Nombre de résultats par page (max: 500, défaut: 30)
`resourceId`	No	Filtrer par ID ressource (référence keywords COMP<id>)
`startMonth`	Yes	Mois de début de période (YYYY-MM) — obligatoire pour l'API
`resourceTypes`	No	IDs de types de ressource — `boond://dictionary/typeOf/resources`.
`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.
`validationStates`	No	États du workflow de validation : waitingForValidation (à valider), validated, rejected.
`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.

Schema Changelog

Changes observed during successful MCP inspections.

Changed19 schema fields changedv2.17.0Sep 26, 2026

changedInput schema / properties / endMonth / description

Previous value: -"Mois de fin de période (YYYY-MM)"New value: +"Mois de fin de période (YYYY-MM) — obligatoire pour l'API"

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

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 / 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"
+}

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+$"
```

addedInput schema / properties / resourceTypes

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

addedInput schema / properties / sort

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

changedInput schema / properties / startMonth / description

Previous value: -"Mois de début de période (YYYY-MM)"New value: +"Mois de début de période (YYYY-MM) — obligatoire pour l'API"

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

addedInput schema / properties / validationStates

Added value: +{
+  "description": "États du workflow de validation : waitingForValidation (à valider), validated, rejected.",
+  "items": {
+    "enum": [
+      "waitingForValidation",
+      "validated",
+      "rejected"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / required

Added value: +[
+  "startMonth",
+  "endMonth"
+]

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"
+}

Changed4 schema fields changedv2.8.0Jun 29, 2026

removedInput schema / properties / endDate

Removed value: -{
-  "description": "Date de fin de période (YYYY-MM-DD)",
-  "type": "string"
-}

addedInput schema / properties / endMonth

Added value: +{
+  "description": "Mois de fin de période (YYYY-MM)",
+  "type": "string"
+}

removedInput schema / properties / startDate

Removed value: -{
-  "description": "Date de début de période (YYYY-MM-DD)",
-  "type": "string"
-}

addedInput schema / properties / startMonth

Added value: +{
+  "description": "Mois de début de période (YYYY-MM)",
+  "type": "string"
+}

First observedv2.1.0May 30, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already carry readOnlyHint/idempotentHint/destructiveHint, and the description adds genuine behavioral context beyond them: the resourceId→keywords COMP<id> conversion quirk (API has no dedicated parameter), the fields parameter being a pure MCP-side projection never sent to the API, and the hard pagination refusal beyond pageSize 500 / page 100. These are non-obvious runtime behaviors an agent must know.

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?

Purpose is front-loaded and the structure is logical: purpose → when/alternatives → API quirk → return → fields note → pagination. The bullets keep it scannable. It is fairly dense but every section earns its place; only minor redundancy with schema (pagination defaults are repeated from the schema, though the 'refus beyond limit' detail is new).

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?

No output schema exists, and the description only states 'Returns: Liste des demandes d'absence correspondantes' without detailing the result structure. For a search tool the list-of-absences return is largely implied, and the description covers the key non-obvious behaviors (fields projection, resourceId conversion, pagination refusal, perimeter join logic). Slightly more output-structure detail would be ideal but is not critical.

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% so baseline is 3, but the description adds real meaning beyond the schema: it explains the required startMonth/endMonth format, the resourceId conversion to keywords COMP<id>, the fields projection behavior (replaces summary, unknown names ignored), and the narrowPerimeter ET-vs-OU join semantics. The resourceId quirk alone is high-value information not derivable from the schema.

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 des demandes d'absence'), a precise resource, and the key filter dimensions (période, ressource, état de validation, périmètre). It explicitly differentiates from siblings: boond_planning_absences_search for the calendar view and boond_validations_search for pending validations, so an agent can pick this tool without inspecting schemas.

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?

Provides explicit 'Quand' (when to use) and 'Plutôt que' (rather than) guidance, naming the two relevant sibling tools and the condition that selects them (calendar view vs pending validations). This is textbook routing guidance with no inference required.

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

Deploy Server

Rechercher des demandes d'absence

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools