The directory envelope (v0.2, authority: manifest). Real entries only — a data source enters on one of three admission routes (E21); an empty list is the honest state, never padded.
| 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?
The readOnlyHint annotation already covers the safety profile. The description adds meaningful behavioral detail beyond the annotation: results contain real entries only, empty lists are honest states, and results are never padded. This is useful context, though it could be more explicit about what an 'envelope' contains.
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 a single dense sentence with the resource name front-loaded and every clause carrying semantic weight. It is concise, but the unexplained parentheticals and domain-specific references reduce immediate readability.
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?
There is no output schema, so the description should carry the burden of explaining what the tool returns. It vaguely promises a 'directory envelope' with real entries but does not define the entry shape, fields, or relationship to manifest.get, and 'E21' is left unexplained. For a parameterless tool this is less severe, but an agent still lacks enough detail to interpret the result confidently.
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 tool has zero parameters and an empty input schema, so the parameter-semantics burden is minimal; the baseline for zero-parameter tools is 4. The description correctly avoids inventing parameter details where none exist.
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 names a resource ('directory envelope') and a key guarantee ('real entries only'), so it is not a pure tautology. However, it never states the operation in plain terms such as 'returns the directory of admitted data sources,' and jargon like 'v0.2, authority: manifest' and 'E21' obscures the basic purpose. It only partially distinguishes itself from sibling tools like manifest.get.
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?
There is no explicit guidance on when to use this tool versus alternatives. The description hints at the manifest as an authority but never points to manifest.get or explains how directory.get differs from other read-only listing tools, leaving the agent to guess at the appropriate selection context.
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.
The tools are strongly namespaced and most have a clear 'use for' hint, so an agent can usually select correctly. A few near-neighbour pairs, such as fedlex.get_citations vs fedlex.get_references and facts.badge vs facts.latest, require careful reading but are still distinguishable.
The <domain>.<snake_case_action> style is consistent and the fedlex/lindas families are predictable. However, several noun-style names such as meta.tools, lindas.observations, and facts.badge deviate from the verb_noun pattern, and the variety of get_/read_/list_/find_ verbs adds minor noise.
With 52 tools, this is a very large MCP surface for one server; while each tool appears individually purposeful, the combined set is heavy for an agent to explore and select from. The gateway would be more manageable split into separate legal, data, and meta servers.
The Fedlex cluster covers the full legal-research workflow: search, version resolution, reading, comparison, citation checking, history tracing, consultations, and official publications. The LINDAS cluster covers cube discovery, schema inspection, filtering, and label resolution, and the directory/meta tools complete the capability-discovery loop. There are no obvious dead ends or critical missing operations.