Skip to main content
Glama

Hal Fr Structure

hal_fr_structure
Read-onlyIdempotent

Research-structure (lab/department) lookup.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "CNRS"
    },
    "name": "hal_fr_structure"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNo1-1000 (default 25).
queryYes

Output Schema

NameRequiredDescriptionDefault
responseNoStructure search results
responseHeaderNoResponse metadata

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.5/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds only the clarification that a 'structure' means a lab or department; it says nothing about matching behavior (exact vs. fuzzy name match), result shape, or pagination limits beyond the schema's rows note.

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?

It is a single five-word fragment with zero waste, so it is certainly concise. But conciseness here shades into under-specification: the parenthetical is front-loaded well, yet the whole definition is too thin to orient an agent before it opens the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations cover safety. Still, for a tool whose key ambiguity is what 'structure' means and how query is matched, the description leaves the agent to guess whether it accepts acronyms, partial names, or IDs — a meaningful gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: rows is documented ('1-1000 (default 25)') while query has no description in the schema, and the examples ('CNRS', 'Laboratoire d'Informatique') do imply that query is a structure name. The description itself contributes nothing to parameter meaning, but the schema examples partially compensate, keeping this near the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a lookup of research structures and parenthetically disambiguates the jargon as 'lab/department', which is genuinely useful. However, it never states the domain (HAL French research archive) or the verb explicitly, and 'research-structure' remains opaque without the parenthetical. It hints at a resource but does not clearly separate itself from hal_fr_search or hal_fr_author.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance at all: no mention of when to pick this over hal_fr_search, hal_fr_author, or hal_fr_get. The agent must infer from the sibling name alone that this resolves lab/department entities rather than publications or authors.

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.