Tulina

fr_aides_search

Read-only

Shortlist of French public aid (grants, loans, guarantees, calls for projects) for a company/project — data.aides-entreprises.fr database (State reference, ~2,400 active aids, updated daily, the database prunes expired ones).

Returns the DETERMINISTIC filter (geo by hierarchy commune→dept→region→ France/EU + headcount band + nature + deadline) with the measured funnel (funnel). ⚠️ SECTOR relevance can NOT come from the database (its profile tagging is 99% over-inclusive) nor from lexical scoring: it is UP TO YOU to re-rank the shortlist by reading name/purpose. Anti-hallucination rule: keep only ids, then re-render each record via fr_aides_get(id) — NEVER rephrase name/purpose from memory, quote literally.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "fr_aides_search"
  }
}

Input Schema

Name	Required	Description
`q`	No	lexical AND filter (coarse pre-filter, NOT a relevance sort).
`_org`	No	Org (id) de CET APPEL. `oto_list_orgs()`.
`insee`	No	INSEE commune code (preferred — e.g. "31555" Toulouse).
`limit`	No	records returned (default 50; `count` = filtered total).
`_group`	No	Équipe (id) de CET APPEL, sous son org parente.
`nature`	No	substring of the aid type, matched against the French source values ("subvention", "prêt", "garantie", "avance", "exonération", "prestation"...).
`offset`	No	pagination.
`_run_id`	No	OBLIGATOIRE à chaque appel dès `run_start` ou `data_claim_next` : sans lui, l'écriture sur une ligne réservée est refusée. Hérité seulement si le serveur tient un run actif — n'y compte pas.
`_project`	No	Projet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
`effectif`	No	number of employees (filters the bands; aids with no restriction stay).
`_instance`	No	Instance de connecteur PRÉCISE (un credential exact). `oto_instance(op='list')`.
`code_postal`	No	fallback when no INSEE code (best-effort resolution).
`echeance_avant`	No	YYYY-MM-DD — aids with a deadline closing before the date (call-for-projects watch; excludes permanent aids).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: it discloses the database's maintenance behavior (expired aids pruned, updated daily), the known defect in the source's profile tagging (99% over-inclusive), the returned `funnel` measurement, and an explicit anti-hallucination constraint against rephrasing name/purpose from memory. That is exactly the behavioral context an agent needs and cannot get from the annotation.

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?

Front-loaded with the one-line purpose, then the filtering model, then the caveat and the cross-reference rule — a sensible order for an agent scanning for fit. It is dense and uses emoji/warning styling, and a couple of clauses (the tagging critique, the anti-hallucination rule) could be tightened, but nearly every sentence carries operational value.

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?

For a 13-parameter read-only search with no output schema, the description supplies the missing output context (a `funnel` measurement, `id`-only records) and the required follow-up call for readable detail. It does not enumerate the record fields returned, but it explicitly routes the agent to `fr_aides_get` for that, which covers the gap adequately.

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 coverage is 100%, so a baseline of 3 applies, but the description adds real meaning: it explains that geo filtering works through the commune→dept→region→France/EU hierarchy and that `effectif` matches headcount bands while aids with no restriction remain in the results. It also reframes `q` semantically as a coarse AND pre-filter rather than a ranking signal.

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 and resource ("Shortlist of French public aid") and pins down the exact source (data.aides-entreprises.fr, ~2,400 active aids, updated daily) plus scope (grants, loans, guarantees, calls for projects). It also separates itself from the sibling fr_aides_get by casting this tool as the list/shortlist step and that one as the detail re-render step.

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?

Explicitly defines what the tool does and does not do: geo/headcount/nature/deadline filtering is deterministic and handled here, while sector relevance must be re-ranked by the caller, and `q` is called out as a coarse AND pre-filter rather than a relevance sort. It also prescribes the correct follow-up path (re-render each kept `id` via `fr_aides_get`). The only gap is that it does not compare against other aid/financement search siblings, but those are far enough afield that this is minor.

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

All Tulina 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?