Retrieve contract text split by article to verify or cite a precise clause. Optionally filter by article IDs for targeted review.
Renvoie le texte d'un contrat, découpé par article, pour vérifier ou citer une clause précise.
| Name | Required | Description | Default |
|---|---|---|---|
| chunk_ids | No | Limiter à ces articles (ex. « c07-2 »). Vide = tout le contrat. | |
| contract_id | Yes | Identifiant renvoyé par search_data_room, ex. « c07 ». |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does disclose that output is chunked by article, which is genuinely useful, but says nothing about permissions, whether the call is safe/read-only, rate limits, or how a full-contract dump behaves for very long documents.
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 that front-loads the action and the output structure, then the purpose. No filler, no restatement of the tool name.
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 two-parameter getter with full schema coverage and a named sibling, one sentence plus the schema is close to sufficient — the article-level return shape is stated. The main gap is the lack of any workflow note about obtaining contract_id first, and there is no output schema to fall back on.
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 100%, so both parameters are already documented in the schema with format examples ("c07", "c07-2") and the empty-array default. The description adds no parameter-level detail, so the baseline 3 applies.
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?
Specific verb+resource: it returns contract text split by article. The clause-verification framing sharpens what the resource is for. It doesn't explicitly contrast itself with search_data_room, which is the natural sibling, but an agent can distinguish a full-text fetch from a search without much trouble.
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?
"pour vérifier ou citer une clause précise" implies the use case (deep-read a known contract for a specific article) but gives no explicit when-not or routing rule versus search_data_room. The dependency on a contract_id from search_data_room is only hinted at in the schema, not stated as a workflow step.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.