USE THIS to verify a French social-security number (NIR / numéro de sécurité sociale, INSEE) before relying on it — do not guess the key. Checks the 13-digit body (Corsica 2A/2B handled) and the mod-97 two-digit key. Validates structure only.
| Name | Required | Description | Default |
|---|---|---|---|
| nir | Yes | The French NIR: 13 digits + 2-digit key (spaces ignored). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description details that it checks the 13-digit body with Corsica handling and the mod-97 key. It states 'Validates structure only,' but does not specify the return format, which would be helpful given no output schema.
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 extremely concise, using two sentences that front-load the imperative 'USE THIS' and then deliver key details. No unnecessary words or redundancy.
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 single-parameter validation tool, the description covers purpose, key behavioral details, and limitations. It lacks explicit mention of the return type, which is a minor gap given no output schema, but overall sufficient for the tool's simplicity.
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 input schema already describes the NIR format (13 digits + key, spaces ignored). The description adds semantic value by noting that Corsica codes (2A/2B) are handled and advising against guessing the key, enhancing parameter understanding 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 clearly states the tool verifies a French NIR, specifying the exact resource and actions. It distinguishes from sibling validation tools by focusing on the French social-security number and mentioning the specific format and key check.
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 explicitly advises using this tool when relying on a NIR ('do not guess the key'), providing clear when-to-use guidance. It also clarifies that it only validates structure, implying limitations, but lacks direct comparison to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a specific identifier or operation (e.g., validate_iban, parse_date, is_holiday). Even similar tools like validate_isbn and validate_isbn10 are distinct by version. There is no overlap or ambiguity.
Most tools follow a verb_noun pattern (validate_xxx, parse_xxx, format_currency). The exception is 'next_holiday', which uses an adjective instead of a verb. Otherwise consistent.
With 47 tools, the set is very large. While each tool is distinct, the count exceeds the recommended range (25+ is considered too many) and may overwhelm users or agents.
Covers a wide array of international identifiers and utilities, but notable gaps exist (e.g., no Canada SIN, India PAN, Mexico CURP). The set is broad but not exhaustive for the domain of data validation.