Skip to main content
Glama

search

Read-onlyIdempotent

Searches all sources (French and European case law, codes and statutes, Journal officiel, collective agreements, doctrine), expanding to legal synonyms. Entry point for an open question; for one specific court, use search_case_law. A citation ("Cass. soc. 11 mai 2022", an ECLI, an appeal number) is recognised and searched as such. Singular and plural are searched together; "in double quotes": the exact word. Query in French: the data is French (some ECHR/CJEU texts are English only).

Example: search(query="harcèlement moral fonctionnaire")

Args: query: keywords or a citation; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words sources: dila, jade (administrative courts: JADE + TA/CAA/CE open data), legi, cedh, cjue, kali, jorf, doctrine, cnil (empty: all) sort: relevance | date_desc | date_asc date_min: YYYY-MM-DD (all sources) date_max: YYYY-MM-DD limit: results (max 100; at most 50 per source per call, no offset: when more exist, truncated and note say so and name the tool that paginates) expand_synonyms: expand to legal synonyms (default true)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNorelevance | date_desc | date_ascrelevance
limitNoresults (max 100; at most 50 per source per call, no offset: when more exist, `truncated` and `note` say so and name the tool that paginates)
queryYeskeywords or a citation; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words
sourcesNodila, jade (administrative courts: JADE + TA/CAA/CE open data), legi, cedh, cjue, kali, jorf, doctrine, cnil (empty: all)
date_maxNoYYYY-MM-DD
date_minNoYYYY-MM-DD (all sources)
expand_synonymsNoexpand to legal synonyms (default true)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"results (max 100)"New value: +"results (max 100; at most 50 per source per call, no offset: when more exist, `truncated` and `note` say so and name the tool that paginates)"
    • changedInput schema / properties / sources / description
      Previous value: -"dila, jade, legi, cedh, cjue, kali, jorf, doctrine (empty: all)"New value: +"dila, jade (administrative courts: JADE + TA/CAA/CE open data), legi, cedh, cjue, kali, jorf, doctrine, cnil (empty: all)"
  2. Changed1 schema field changed
    • changedInput schema / properties / date_min / description
      Previous value: -"YYYY-MM-DD (legi, jorf)"New value: +"YYYY-MM-DD (all sources)"
  3. Changed6 schema fields changed
    • changedInput schema / properties / date_max / description
      Previous value: -"AAAA-MM-JJ"New value: +"YYYY-MM-DD"
    • changedInput schema / properties / date_min / description
      Previous value: -"AAAA-MM-JJ"New value: +"YYYY-MM-DD (legi, jorf)"
    • changedInput schema / properties / expand_synonyms / description
      Previous value: -"élargir aux synonymes (défaut oui)"New value: +"expand to legal synonyms (default true)"
    • changedInput schema / properties / limit / description
      Previous value: -"nombre de résultats (max 100)"New value: +"results (max 100)"
    • changedInput schema / properties / query / description
      Previous value: -"mots-clés ou référence"New value: +"keywords or a citation; OR/AND/NOT/NEAR in UPPERCASE between two words are operators (NEAR = within 10 words); lowercase words are plain words"
    • changedInput schema / properties / sources / description
      Previous value: -"sous-ensemble de dila, jade, legi, cedh, cjue (vide = toutes)"New value: +"dila, jade, legi, cedh, cjue, kali, jorf, doctrine (empty: all)"
  4. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. Beyond that the description discloses real operational behavior: max 100 results, at most 50 per source per call, no offset, and that truncation is signalled via `truncated`/`note` along with the name of the paginating tool. Missing only return-shape detail, which the output schema covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening paragraph and example are front-loaded and earn their place, but the per-argument Args block duplicates the input schema almost word for word, consuming tokens without adding information. Structure is clear and navigable; the repetition is the main inefficiency.

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?

For a 7-parameter, multi-source search tool, the definition covers query syntax, language requirement, source enumeration, date format, result caps, truncation/pagination behavior, and sibling routing. With annotations and an output schema already present, nothing an agent needs in order to call it correctly is missing.

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% and the Args block largely restates it verbatim, so credit only comes from the genuinely additive parts: the query-in-French constraint, singular/plural being searched together, double quotes forcing an exact word, and the worked example query. Those change how an agent writes the `query` value.

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?

A precise verb (searches) plus an explicit resource scope: French and European case law, codes and statutes, Journal officiel, collective agreements, doctrine. It also distinguishes itself from the sibling search_case_law by naming the case where that tool is preferred, so the agent can route without inspecting either schema.

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?

Usage is stated directly: 'Entry point for an open question; for one specific court, use search_case_law.' It further states that citations (Cass. soc. format, ECLI, appeal number) are auto-detected and searched as citations, and that queries must be in French because the corpus is French — both are conditions that change how an agent should call it.

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.

Resources