Skip to main content
Glama
MCP Agent Operations

MCP Agent Operations

reference_load

Read-onlyIdempotent

Load recursive text references from all matching allowed folders, returning aggregated content in the requested order for deterministic agent operations.

Instructions

Load recursive text references aggregated across every matching allowed folder.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "names": "<names>"
    },
    "name": "reference_load"
  }
}

Input Schema

NameRequiredDescriptionDefault
namesYesOne to thirty-two unique relative paths in requested result order.

Output Schema

NameRequiredDescriptionDefault
okYes
errorsNo
referencesNo
catalog_revisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.11.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered structurally. The description contributes the folder-aggregation and "allowed" (permission-scoped) aspects, but says nothing about how duplicates or missing references are handled. With the annotation bar already met, this is a modest but real addition.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb and no padding. The density of qualifiers ("recursive", "aggregated", "matching allowed") makes it slightly harder to parse than its length warrants, but nothing is redundant.

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

Completeness3/5

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

The tool is simple (one parameter, output schema present, annotations present), so the definition does not need to be long. However, an agent still cannot tell what "allowed folders" means operationally or how this differs from the refresh and skill_resource load siblings, which is the main completeness 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 description coverage is 100% and the single `names` parameter is fully documented, including the one-to-thirty-two bound, uniqueness and result ordering. The description adds no meaning beyond that. A baseline 3 is appropriate when the schema does all the work.

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?

"Load recursive text references" gives a verb and a resource, but "recursive text references" is jargon that doesn't clearly resolve to a concrete artifact, and "aggregated across every matching allowed folder" adds scope without saying what a caller actually receives. Sibling names like reference_refresh and skill_resource_load suggest overlapping territory that the description never disambiguates.

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 statement of when to call this versus reference_refresh or skill_resource_load, and no note on prerequisites such as whether references must exist or be refreshed first. The only guidance-like phrase is the scope restriction (allowed folders), which describes behavior rather than selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.