Skip to main content
Glama

Procedure References

procedure_references
Idempotent

Retrieve every raw incoming or outgoing reference edge for a procedure, preserving provider-specific flags and resolving endpoints through containment for accurate call analysis.

Instructions

Return every raw incoming or outgoing reference edge for one procedure. Endpoint procedures are resolved only from provider containment. Ghidra preserves detailed reference flags. Hopper preserves native CallReference classifications and exact endpoints while leaving unavailable detailed flags explicit.

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": {
      "direction": "outgoing",
      "procedure": "main"
    },
    "name": "procedure_references"
  }
}

Input Schema

NameRequiredDescriptionDefault
documentNoThe active target's provider document name; use open_binary to switch targets
directionNoDirection in which to traverse or compare relationships.
procedureYesThe procedure name or address

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

The description adds genuine behavioral context beyond the annotations: endpoint procedures come only from provider containment, and result fidelity varies by provider (Ghidra keeps detailed reference flags, Hopper keeps native CallReference classifications and exact endpoints while marking unavailable flags explicitly). That is useful, non-obvious disclosure. It does not, however, address the notable readOnlyHint=false annotation for what reads like a pure retrieval, nor does it say whether any state is touched, so part of the behavioral burden is still unmet.

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?

The core capability is front-loaded in the first sentence, and the remaining three sentences are short and on-topic. The provider-specific sentences are somewhat implementation-flavored and could be condensed, but nothing is redundant padding.

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?

With no output schema, the description carries the burden of describing what a returned reference edge contains. It covers endpoint resolution and flag/classification fidelity but never says what fields an edge exposes or in what shape they arrive. For a moderately complex, provider-dependent analysis tool, that leaves 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 description coverage is 100%, so all three parameters are already documented in structured data, and the description adds only the framing 'for one procedure' plus the incoming/outgoing distinction. The endpoint-containment sentence is a semantic constraint loosely relevant to the procedure and document parameters, but it is not parameter-level guidance. Baseline 3 is appropriate.

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

Purpose4/5

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

The first sentence gives a specific verb and resource: 'Return every raw incoming or outgoing reference edge for one procedure.' That is far more precise than the bare title. It does not, however, contrast itself with plausible siblings such as procedure_callers or procedure_callees, so the agent must infer that 'raw edge' means the lower-level, unfiltered view.

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 explicit when-to-use or when-not-to-use guidance. The word 'raw' hints that this is a lower-level alternative to a caller/callee listing, but no alternative tool is named and no condition is given for choosing between them. The agent is left to infer the selection rule from the adjective alone.

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

Deploy Server

Other Tools