Skip to main content
Glama

Rechercher un établissement de formation

search_training_centers
Read-only

Recherche des établissements de formation français : organismes de formation, CFA (apprentissage), centres de bilan de compétences et établissements d'enseignement supérieur. Filtrable par ville, code postal, département, région et type. En fournissant certificationId, renvoie plutôt les établissements qui préparent ce diplôme — c'est ainsi qu'on répond à « où préparer ce diplôme » et « dans quelles villes ». Renvoie « total », le nombre d'établissements correspondants, et « results », une page d'au plus 20. Quand le référentiel en compte trop pour être dénombrés, « total » vaut null et « totalAtLeast » porte une borne basse : dire alors « plus de N », jamais « N ». Avec certificationId, « total » vaut null sans borne : cette collection n'en fournit aucune. EN: Search French training establishments: training providers, apprenticeship centres, skills-assessment centres and higher-education institutions. Filter by city, postcode, department, region and type. Passing certificationId instead returns the establishments preparing that diploma. Returns « total » and « results ». When the reference data holds too many to count, « total » is null and « totalAtLeast » carries a lower bound: say « more than N », never « N ». With certificationId, « total » is null with no bound.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoRecherche libre sur le nom et la ville. Un NOM d'établissement se cherche ici seul, ville incluse dans q si besoin — jamais cumulé avec les filtres city ou postalCode : la commune administrative d'un organisme diffère souvent de la ville de son enseigne, et le cumul renvoie alors un total de 0 à tort. Les filtres de lieu servent aux recherches par type ou par domaine, pas aux noms propres. EN: Free-text search on name and city. Search an establishment NAME here alone, city included in q if needed — never combined with the city or postalCode filters: an organisation's registered town often differs from the town in its brand name, and combining then wrongly returns a total of 0. Location filters serve type or domain searches, not proper names.
cityNoNom exact de la ville. Ne sert pas à retrouver un nom d'organisme — mettre alors tout dans q, jamais ici. EN: Exact city name. Never use it to find an organisation by name — put everything in q instead.
typeNoType d'établissement. Valeurs acceptées : organisme_formation, centre_formation_apprentis, centre_bilan_competences, etablissement_enseignement_superieur. EN: Establishment type. Accepted values: organisme_formation, centre_formation_apprentis, centre_bilan_competences, etablissement_enseignement_superieur.
limitNoNombre de résultats, 1 à 20 (défaut 10). EN: 1 to 20 (default 10).
regionNoNom de la region. EN: Region name.
radiusKmNoRayon en kilomètres, de 1 à 200 — 15 km est un bon départ, à élargir si vide. Pour « près de X » ou « autour de X », ou quand une petite ville ne donne rien : resolve_location d'abord, puis ses latitude/longitude ici. Le rayon REMPLACE city et postalCode, jamais en cumul — les résultats sont triés par distance croissante et portent distanceKm. Il sert aux recherches par type ou par domaine, pas aux noms propres : un nom d'établissement se cherche toujours dans q seul. EN: Radius in km, 1 to 200 — 15 km is a good start, widen if empty. Resolve the city first, then pass its latitude/longitude here. The radius REPLACES city and postalCode, never combined — results are sorted by distance and carry distanceKm. It serves type or domain searches, never proper names: an establishment name still goes in q alone.
aroundLatNoLatitude du centre du rayon, prise telle quelle dans la réponse de resolve_location. Toujours avec aroundLng et radiusKm. EN: Latitude of the radius centre, taken verbatim from resolve_location. Always with aroundLng and radiusKm.
aroundLngNoLongitude du centre du rayon, prise telle quelle dans la réponse de resolve_location. EN: Longitude of the radius centre, taken verbatim from resolve_location.
departmentNoDépartement au format « code - nom », ex. « 06 - Alpes-Maritimes », telle que renvoyée par resolve_location. Le nom seul ne ramène rien. EN: Department as « code - name », e.g. « 06 - Alpes-Maritimes », as returned by resolve_location. The name alone matches nothing.
postalCodeNoCode postal. Même règle que city : jamais cumulé avec un nom d'organisme dans q. EN: Postcode. Same rule as city: never alongside an organisation name in q.
certificationIdNoIdentifiant d'une certification : renvoie les établissements qui la préparent, en ignorant les autres filtres. EN: Certification id: returns the establishments preparing it, ignoring other filters.

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and destructiveHint. The description adds substantial behavioral context: results are capped at 20, 'total' can be null with a 'totalAtLeast' lower bound, certificationId mode returns no bound at all, radius replaces city/postalCode, results are sorted by distance and carry distanceKm, and certificationId ignores other filters. This far exceeds what the annotations convey.

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 dense, front-loaded with purpose, and every caveat about q, radius, certificationId, and total semantics is operationally valuable. It is long, partly due to bilingual FR/EN duplication, but the structure is logical and the length is justified for an 11-parameter tool with no output schema.

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?

With no output schema, the description must explain return semantics, and it does: 'total', 'results', the 20-item page cap, null behavior and totalAtLeast, certificationId's no-bound case, and radius-specific fields. It also covers parameter precedence and the dependency on resolve_location. No essential calling information appears missing.

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 baseline applies and the description does not need to document each parameter. The top-level description adds useful global semantics around total/totalAtLeast and certificationId behavior, but it does not add per-parameter meaning beyond what the input schema already provides.

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 states a specific verb and resource: 'Recherche des établissements de formation français', enumerates the establishment types covered, and clearly contrasts the certificationId search mode ('plutôt les établissements qui préparent ce diplôme'). This makes it easy to tell apart from singular tools like get_training_center and from search_trainings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to/when-not-to guidance: use q alone for establishment names, never combined with city/postalCode; use certificationId for 'où préparer ce diplôme'; resolve a city with resolve_location before using radiusKm. However, it does not explicitly name or contrast sibling tools such as search_trainings or get_training_center, so alternative-selection guidance is implicit rather than direct.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool targets a clearly distinct resource and action: searches return lists, get tools return single records, and compare_skills, get_similar_jobs, get_job_pathways, and resolve_location each have unique purposes. Even the search_trainings/search_training_centers pair is unambiguous because one yields programmes and the other establishments.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: get_* for records, search_* for queries, plus list_job_sectors, resolve_location, and compare_skills. The slight singular/plural variation between get_training and search_trainings does not break the pattern.

Tool Count5/5

Thirteen tools is well-scoped for a career-guidance server covering jobs, certifications, training programmes, training establishments, location resolution, and skill matching. Each tool earns its place and none feel redundant or decorative.

Completeness5/5

The surface covers the full career-guidance workflow: searching jobs and certifications, retrieving details, finding pathways, locating nearby training, listing sectors, resolving locations, comparing skills, and exploring similar jobs. Every get tool has a clear search entry point, so there are no dead ends.