Mission Museaux

Chercher des missions de bénévolat / Find volunteering missions

chercher_missions_benevolat

Read-onlyIdempotent

Find animal volunteering missions in France (shelters, wildlife, horses) near a town, in a department or nationwide, from API Engagement data. Use it to help someone volunteer. Returns up to 25 missions with organisation, place, dates and the Mission Museaux page to apply. Accepts French or English; replies in French, or English with langue "en".

Input Schema

Name	Required	Description	Default
`type`	No	Kind of mission: tous (all, default), benevolat (volunteering), service_civique (French civic service, ages 16 to 25) or volontariat (other volunteer schemes).	tous
`langue`	No	Response language: "fr" (French, default) or "en" (English). A request written in English is answered in English even without it.	fr
`limite`	No	Number of missions to return (whole number, 1 to 25, default 10); a larger value is lowered to 25. Use decalage for the next page.
`commune`	No	French town name or 5-digit postcode (string, 2 to 80 characters), e.g. "Nemours", "77140" or "Chaumont 52" (department number to tell namesakes apart). France only; a place abroad returns no result.
`decalage`	No	Number of missions to skip, for paging (whole number, 0 to 500, default 0), e.g. 10 for the second page of 10.
`latitude`	No	Latitude of the search centre in decimal degrees (number, -90 to 90), e.g. 48.267. Give it with longitude, instead of commune.
`rayon_km`	No	Search radius in km around commune or the coordinates (number, 1 to 100, default 30). Without a centre or departement, all of France.
`longitude`	No	Longitude of the search centre in decimal degrees (number, -180 to 180), e.g. 2.693. Give it with latitude, instead of commune.
`departement`	No	Department or region instead of a radius (string): code or name, several separated by commas, e.g. "77", "2A", "Bretagne" or "75, 92, 93". A commune given with it only sorts by distance.

Output Schema

Name	Required	Description
`type`	Yes
`total`	Yes
`centre`	Yes
`rappel`	Yes	How to apply: from the mission's page on Mission Museaux.
`donnees`	Yes	Where the missions come from: API Engagement, under the Licence Ouverte 2.0.
`decalage`	Yes
`missions`	Yes
`rayon_km`	Yes
`homonymes`	Yes	When several towns have exactly the given name and no department tells them apart; null otherwise.
`plus_proche`	Yes	In an empty answer around a town or point, the closest mission of the same type beyond the radius, anywhere in France.
`total_exact`	Yes
`departements`	Yes
`indisponible`	No	Present when no search could take place (missions not available here, or the daily copy not ready yet).
`lieu_non_couvert`	No	Present when the given town is not a French town: without a requested department, no search took place; Mission Museaux covers France.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 15, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered; the description adds genuinely new behavioral context: the upstream data source (API Engagement), the result ceiling (up to 25 missions with organisation, place, dates and an application page), and the language negotiation behavior between French and English. It stops short of describing pagination behavior explicitly, which the limite/decalage schema handles.

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?

Three sentences, front-loaded with the core purpose and geographic scope before the return content and language rules. Slightly redundant between "Returns up to 25 missions" and the schema's maximum of 25, but overall efficient and free of padding.

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?

With an output schema present, the description need not enumerate return fields, yet it usefully names the key ones. Annotations cover the safety profile and the schema is fully self-documented, so the only real omission is guidance on choosing this tool over the other chercher_* siblings.

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 description coverage is 100%, so the baseline is 3. The description rises above that by synthesizing the three mutually exclusive geographic search modes (near a town, in a department, or nationwide) and by stating the language behavior that governs the langue parameter, both of which help an agent choose parameters rather than just fill them.

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 names a specific verb and resource (finding animal volunteering missions in France), states the scope variants (shelters, wildlife, horses) and the geographic modes (town, department, nationwide), and identifies the data source (API Engagement). This is clearly distinguishable from siblings such as chercher_adoptions or chercher_annonces, which target different resources.

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

Usage Guidelines3/5

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

"Use it to help someone volunteer" gives a purpose context but no explicit when/when-not and no named alternative among the sibling search tools. The geographic-mode hints (commune vs latitude/longitude vs departement) are usage-relevant but are restatements of the schema rather than routing guidance.

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

All Mission Museaux tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?