Read-only MCP server to search and profile 126,000+ French associations and charities (SIREN, RNA, transparency scores) from official public registries.
Scored across 8 tools
Each tool has a recognizable target: NGO lookup by slug (get_ngo), NGO search (search_ngos), ranking (top_ngos), comparison (compare_ngos), causes taxonomy (list_causes), and two guide tools. Minor overlap exists between list_causes and search_ngos (filter by cause) and between top_ngos and search_ngos, but the descriptions make the boundaries reasonably clear.
Nearly all names follow a clean verb_noun snake_case pattern (get_ngo, search_ngos, list_causes, compare_ngos, get_donation_paths). The only deviation is top_ngos, which is noun/adjective-led rather than verb-led, but it remains readable and idiomatic for a ranking endpoint.
Eight tools is well-scoped for a public NGO directory and donation-info site: three discovery tools, one detail tool, one comparison tool, one donation tool, and two guide tools. Every tool maps to a distinct user-facing capability with no filler.
The surface covers discovery (search, ranking, causes), detail (NGO fiche, donation paths), comparison, and editorial guides, which is the core lifecycle for a read-only public-data service. Minor gaps remain: no direct lookup by SIREN/RNA, no listing of guides by category, and no dedicated geography/department listing even though top_ngos filters on them.
Compare 2 à 3 associations par slug : score global, ventilation par pilier, localisation et lien de don.
| Name | Required | Description | Default |
|---|---|---|---|
| slugs | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden. It does disclose the shape of what comes back (scores, per-pillar breakdown, location, donation link), which implies a read-only aggregation, but it says nothing about error behavior for invalid or duplicate slugs, ordering of results, or whether the comparison is cached/computed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that states the operation, its cardinality constraint, and the output facets with zero filler. It could be marginally improved by separating scope from output, but nothing is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description must explain both behavior and returns. It lists the four output components but gives no structure, ordering, or error details, leaving meaningful gaps for a tool whose entire value is the comparison payload.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but there is only one parameter and the description explains that it is a slug-based identification of NGOs and that the count must be 2 to 3. That adds the semantic meaning of 'slug' beyond the schema's type/minItems/maxItems constraints, though it does not clarify slug format or duplicate handling.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ('Compare 2 à 3 associations') and enumerates what the comparison covers (global score, pillar breakdown, location, donation link). It is clearly distinct from single-record siblings like get_ngo, though it never names an alternative explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The use case (side-by-side comparison of a small set of NGOs) is implied by 'Compare 2 à 3 associations', but there is no explicit guidance on when to prefer this over get_ngo (single lookup) or top_ngos (ranking), nor any prerequisites for obtaining slugs.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retourne toutes les options de don pour une association (par slug), avec disclosure d'affiliation.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It implies a read-only retrieval and usefully notes that affiliation disclosure is included, but it does not describe pagination, behavior for invalid slugs, authentication needs, or the shape of returned donation options.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single front-loaded sentence with no filler. Every element, including the affiliation-disclosure note, contributes to understanding the call.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter read tool with no annotations or output schema, the description states the return scope and the affiliation disclosure. However, it omits error handling, empty-result behavior, and any detail about what a donation option contains, leaving meaningful gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It clarifies that 'slug' identifies the association and that the call returns all donation options for that association, but it does not explain slug format, source, or case sensitivity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Retourne') and resource ('options de don') and scopes it to an association identified by slug. It does not explicitly differentiate from any sibling tool, but the sibling list contains no direct donation-options alternative.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool, when not to use it, or which alternative to choose. Usage is only implied by the phrase 'pour une association (par slug)', leaving prerequisites and context unstated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Renvoie titre, résumé, catégorie et URL d'un guide Caritatif.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description has to carry the behavioral burden, and it does disclose the returned field set, which is valuable given there is no output schema. However it says nothing about what happens when the slug is unknown (empty result vs error) or about access requirements, so the picture is only partial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no filler, front-loaded on the verb, and the enumerated return fields are easy to scan. It is efficient, though its brevity borders on under-specification captured in other dimensions.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter read tool the description covers the output surface, which is the main gap when no output schema exists. Missing are the slug's provenance/format and the not-found behavior, which an agent needs before calling it reliably.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the single "slug" parameter has no description in the schema at all. The description never explains what form a slug takes (where an agent obtains one, e.g. from search_guides) or that it is required, so it fails to compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"Renvoie" supplies a concrete verb and "un guide Caritatif" a concrete resource, and it goes further by naming the returned fields (titre, résumé, catégorie, URL). That makes the single-item detail nature clear against search_guides, but the description never explicitly contrasts itself with its siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use statement, no mention of when to prefer search_guides or get_ngo instead, and no prerequisites. The only hint is the singular article in "d'un guide", leaving routing entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fiche complète d'une association par slug : score, ventilation, coordonnées, SIREN, RNA, liens de don.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden. It implies a read-only lookup and usefully discloses what the response contains, but says nothing about behavior on an unknown slug (error vs empty), access restrictions, or how large the record is.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that identifies the lookup key first and then the returned content. The field list is dense but each item conveys what the agent will receive, so little is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description does its part by listing returned fields, which is the main thing an agent needs. However, error behavior for a missing slug and any caveats about the record's size or freshness are absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% and the only hint is the property name 'slug'. The description confirms the lookup key is a slug, which is slight added meaning, but gives no format, source, or example of a valid slug.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource and access pattern: a full record ('fiche complète') of one association looked up by slug, and it enumerates the payload (score, breakdown, contact details, SIREN, RNA, donation links). That clearly separates it from search_ngos or top_ngos, though no sibling is named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this versus search_ngos, compare_ngos, or get_donation_paths, and no prerequisite such as 'requires a slug obtained from search_ngos'. Usage is only implied by the word 'slug'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Liste les causes Caritatif avec slug, libellé, nombre d'associations actives et URL du classement.
| Name | Required | Description | Default |
|---|---|---|---|
| include_counts | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden; it does add real value by disclosing the shape of each returned item, which the missing output schema would otherwise leave unknown. However, it says nothing about ordering, pagination, result volume, or whether the counts are always computed — behavior an agent needs before invoking it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One front-loaded sentence with no filler; the resource comes first and the payload description follows. It is efficient, though the brevity is partly a consequence of omitted information rather than deliberate minimalism.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter list tool with no output schema, disclosing the returned fields is the right instinct, but the one parameter is left unexplained and no usage context is given. Adequate at a glance, incomplete for confident invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter include_counts has 0% schema description coverage and no default value documented. Worse, the description implies the count of active associations is always part of the result, which leaves the role of include_counts entirely ambiguous rather than explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb ('Liste') and a specific resource ('les causes Caritatif'), and enumerates the returned fields (slug, libellé, nombre d'associations actives, URL du classement). This clearly separates it from the NGO- and guide-oriented siblings, although it never explicitly names an alternative tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use or when-not-to-use guidance at all: nothing says whether this is the entry point for discovering causes before calling get_ngo or top_ngos, nor whether it is exhaustive or filtered. The only implicit signal is that it is a listing tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Guides éditoriaux Caritatif (transparence, fiscalité, labels).
| Name | Required | Description | Default |
|---|---|---|---|
| cause | No | ||
| query | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden and discloses nothing: not whether matching is keyword or full-text, not what happens when 'cause' and 'query' conflict, not pagination or result limits. A one-line topic label is insufficient for a search tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is short, but the brevity comes from under-specification rather than economy: an incomplete sentence fragment with no verb and no front-loaded action statement. There is no wasted word, yet nothing earns its place beyond a topic tag.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter search tool with no annotations, no output schema, and no parameter documentation, the definition supplies only subject matter. The agent knows what the guides are about but not how to query them or what it will get back.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters ('cause' and 'query') have 0% schema description coverage, and the description never references them. The agent cannot tell whether 'cause' is a cause ID, a slug, or free text, nor how it interacts with 'query' — a gap the description does nothing to close.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The text is a noun fragment ('Guides éditoriaux Caritatif') that restates the tool name rather than stating an action, adding only topical scope (transparence, fiscalité, labels). There is no verb and nothing to separate it from the sibling get_guide, so an agent cannot tell whether this searches, lists, or fetches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no when-to-use guidance, no exclusions, and never mentions the obvious alternative get_guide or search_ngos. The agent must infer entirely from the name when a keyword search is appropriate versus direct retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recherche paginée d'associations françaises par nom, cause ou ville. Données publiques (RNA, JOAFE).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| limit | No | ||
| query | Yes | Terme de recherche |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses pagination and public data provenance (RNA, JOAFE), but omits return shape, read-only safety, rate limits, and pagination defaults.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences are front-loaded with the core action and search scope. No wording is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the essentials for a simple search tool: action, resource, searchable fields, pagination, and data source. It remains incomplete for a tool without an output schema because it does not describe result shape or pagination defaults.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 33%, with page and limit undocumented. The description adds meaning to query by defining searchable dimensions (name, cause, city) and implies pagination, but does not clarify page/limit defaults, bounds, or behavior beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: paginated search of French associations, searchable by name, cause, or city. It implicitly distinguishes search from single-record retrieval like get_ngo, but does not explicitly name sibling tools or boundaries.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by 'Recherche', making clear this is the lookup tool for associations. However, it gives no explicit when-to-use versus alternatives such as get_ngo, compare_ngos, or top_ngos, and no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Classement par score Caritatif. Filtres optionnels : cause, département, région.
| Name | Required | Description | Default |
|---|---|---|---|
| cause | No | ||
| limit | No | ||
| region | No | ||
| department_code | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure and delivers very little: it states the ordering key but not the sort direction (descending assumed but unstated), the default/maximum result count implied by limit, or the shape of the returned ranking. Nothing is said about whether results are a fixed global top-N or a filtered subset, which materially changes interpretation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the ordering criterion before the filters, with no filler. It is efficient, though the terseness edges toward under-specification rather than pure concision.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A four-parameter, zero-required, annotation-free tool with no output schema needs the description to explain defaults, the limit cap, and what a "score Caritatif" ranking actually returns. Almost all of that is missing, leaving the agent to guess at result set size and filter value formats.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description should compensate, but it only names three of the four parameters (cause, département, région) and omits limit entirely. It also silently maps "département" onto the parameter named department_code without explaining the expected code format, and gives no hint about accepted cause or region values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description conveys that this returns a ranking ordered by a "score Caritatif", which is a real resource+ordering statement, but it is phrased as a bare noun label with no verb and gives no scope (how many results, top of what universe). It does nothing to separate it from siblings such as search_ngos, compare_ngos or list_causes, which an agent could easily mistake for the same request.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Filtres optionnels" is a restatement of the schema (0 required parameters) rather than guidance. There is no statement of when a ranked list is preferable to search_ngos, no mention of what happens with no filters, and no prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
compare_ngosget_donation_pathsget_guideget_ngolist_causessearch_guidessearch_ngostop_ngos
Add one secure layer between your agents and this server.