boondmanager-mcp-server

Alertes du tableau de bord

boond_alerts_search

Read-onlyIdempotent

Lists configured alert indicators with thresholds to answer what needs attention today: contract endings, probation periods, unvalidated reports, upcoming actions.

Instructions

Liste les indicateurs d'alerte configurés sur le tableau de bord de l'utilisateur (fins de contrat, périodes d'essai, CRA / notes / absences non validés, actions à venir…) avec leurs seuils : période en jours, états visés, périmètre.

Quand : en premier, pour « qu'est-ce qui demande mon attention aujourd'hui ? » — la liste dit quoi surveiller et avec quels seuils ; l'outil *_search du module donne les éléments. Plutôt que : la ressource boond://alerts/me (même contenu en JSON) ; le prompt attention_du_jour enchaîne indicateur → recherche.

GET /alerts renvoie la configuration des indicateurs, pas des occurrences (vérifié le 2026-09-26) : une ligne par indicateur, params.period en jours (-1 = mois précédent), X / Y = IDs d'états ou de types, perimeter (dynamic_data = mes données). Aucun filtre, aucune pagination, pas de /alerts/{id}.
Correspondances : contractsEndedUpcoming → boond_contracts_search period: "ending" ; resourcesProbationaryDateUpcoming → period: "probationEnding" ; timesReportsWithNoValidation / expensesReportsWithNoValidation / absencesReportsWithNoValidation → boond_validations_search (documentTypes, waitingForValidation) ; actionsUpcoming → boond_actions_search period: "started".

Returns : une ligne par indicateur (module, indicator, paramètres, cadence de rapport) et structuredContent.items[]. Lecture seule.

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

Name	Required	Description	Default
`fields`	No	Projection : attributs à afficher par résultat (ex: ['title','updateDate']). Absent = résumé standard. Noms inconnus ignorés.

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.

Addedv2.17.0Sep 26, 2026

TDQS

A5/5.0

Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description goes further by stating 'Lecture seule', clarifying that GET /alerts returns configuration not occurrences, noting no filters/pagination, and explaining that `fields` is client-side projection never sent to the API. This is rich behavioral context beyond 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 description is long but every section serves a purpose: main purpose, when to use, alternatives, technical details, return structure, and parameter guidance. It uses clear labels ('Quand:', 'Plutôt que:', 'Returns:', 'fields:') and front-loads the primary use case. No redundant or 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?

The tool is relatively complex (configuration vs. occurrences, mapping to multiple search tools), and the description covers all necessary aspects: the meaning of `period`, `perimeter`, state IDs, and the absence of filters/pagination. It also explains the output structure and provides the `fields` parameter semantics. With an output schema present, return values are already defined; the description fills in the behavioral context needed for correct invocation.

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?

Although the schema fully describes the `fields` parameter (100% coverage), the description adds meaningful semantics: it explains that `fields` replaces the summary with only listed attributes, that unknown names are ignored, and that it should be used on large pages. This goes beyond the schema's description and helps the agent use the parameter effectively.

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 tool lists alert indicators configured on the user's dashboard, with specific examples (contract endings, trial periods, CRA/notes/absences not validated, upcoming actions). It distinguishes itself from sibling search tools by explaining it returns configuration, not occurrences, and explicitly notes the difference from `boond://alerts/me`.

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 explicit usage guidance: 'Quand : en premier, pour « qu'est-ce qui demande mon attention aujourd'hui ? »' and 'Plutôt que :' naming alternatives. It also maps each indicator type to the corresponding search tool and parameters, leaving no ambiguity about when to use this vs. alternatives.

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

Deploy Server