French phone format (ARCEP numbering plan): 10-digit national or +33/0033 → E.164, grouped mention, kind mobile/geo/voip/overseas. No subscriber lookup. Paid $0.01 USDC Base x402.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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?
With no annotations, the description carries full behavioral burden. It usefully discloses the paid fee ($0.01 USDC Base x402), the privacy limitation (no subscriber lookup), and the classification outputs. However, it does not explain error/validation behavior for malformed numbers, whether the operation is read-only, or the exact shape of the returned result, leaving some behavioral ambiguity.
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 two dense sentences with no filler. Each phrase adds value: numbering plan, input formats, output types, privacy limitation, and cost. The core purpose is front-loaded, and the limitations/price are appended efficiently.
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 zero-parameter tool without an output schema, the description covers inputs, outputs, classification categories, limitations, and cost. The only notable gap is the absence of an example or explicit statement of the returned value's structure, but the tool's low complexity makes the description adequate.
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?
Parameter count is 0, so the baseline is 4. The description adds meaningful input semantics by defining which phone-number formats are accepted and what transformations/classifications are produced, compensating for the empty input schema. No explicit parameter name is given, but with additionalProperties allowed and zero defined parameters, an agent can reasonably infer the phone number is the subject of the request.
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 identifies the resource (French phone numbers under the ARCEP numbering plan) and the core transformation (10-digit/+33/0033 → E.164, grouped French format, and line kind). It stops short of a single explicit verb like 'formats' or 'validates', but the meaning is unambiguous and it distinguishes itself from the sibling tools, none of which handle phone numbers.
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?
It specifies accepted input forms ('10-digit national or +33/0033') and explicitly states a non-use case ('No subscriber lookup'), which tells an agent when not to use this tool. It does not explicitly compare against alternatives, but no sibling is a phone formatting/classification tool, so the context is sufficient.
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.
Many tools cover adjacent legal concepts such as down payments (acompte/arrhes), payment deadlines (due_date/due_eom/days_late), and identifier checks (check_siret/siren_from_siret/vat_key/eori), which can cause misselection. The descriptions do distinguish them clearly, but the sheer volume of overlapping categories still creates boundary confusion for an agent.
All tool names use lowercase snake_case and are mostly short, readable French legal nouns or noun phrases, so there is a predictable stylistic pattern. The mix of French and English names and the occasional verb-led names like check_siret or siren_from_siret prevent a perfect score.
With 68 tools, this server is far beyond the well-scoped 3-15 tool range and even beyond the 50+ extreme-mismatch threshold. Each tool is a tiny one-purpose helper, but the set as a whole is overwhelming and should be grouped into fewer, broader tools or split into multiple servers.
The tool surface covers an impressively broad range of French legal needs: statutory invoice mentions, payment penalties, holidays, VAT calculations, identifier checks, warranties, withdrawal rights, and dunning steps. There are no obvious dead ends, and mention_fields acts as a completeness checklist for required invoice mentions.