Skip to main content
Glama
architectural_modeling_workflow

architectural_modeling_workflow

by Lsc1123

project_link_authority

Destructive

Links an existing JSON fact table as the sole semantic authority for the project, requiring reads and reconciliation of actual changes before any refresh.

Instructions

Link an existing JSON fact table as sole semantic authority. Refresh only after reading/reconciling its actual changes.

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": {
      "expected_revision": "<expected_revision>",
      "path": "<path>",
      "change_summary": "<change_summary>"
    },
    "name": "project_link_authority"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
change_summaryYes
expected_revisionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the agent is warned this is an unsafe mutation; the description adds real context on top by establishing that the link confers exclusive ("sole") authority and that refreshes should follow reconciliation. What is missing is the part that matters most for a destructive link: what happens to a previously linked authority, whether the operation is reversible, and what 'reconciling' concretely requires. The added context is genuine but incomplete.

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?

Two sentences, no filler, with the core action stated first and the caution second. It is well front-loaded and every clause does work; it is simply too short for the complexity being described rather than padded.

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, but the definition is still thin for a destructive, non-idempotent tool with three undocumented required parameters. Nothing tells the agent how expected_revision behaves on conflict or what happens to any existing linked authority, which are exactly the gaps structured fields leave open. The description does not close them.

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

Parameters2/5

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

Schema description coverage is 0% across three required parameters, so the description carries full burden and largely drops it. "Its actual changes" gestures at change_summary and "refresh" vaguely evokes expected_revision, but the critical semantics of expected_revision (an optimistic-concurrency guard that will fail the call if stale) and the format/role of path are never explained. An agent must guess at parameter meaning before making a destructive call.

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 names a verb ("Link") and a resource ("an existing JSON fact table") and adds a scope claim ("sole semantic authority"), so the general idea is graspable. However, "semantic authority" is jargon that is never grounded, and nothing distinguishes this from sibling tools that also mutate project state (project_update, evidence_register, project_init). An agent cannot confidently tell when this tool is the right one.

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?

The only usage instruction is a caution attached to refreshing ("Refresh only after reading/reconciling its actual changes"), which is a sequencing rule, not a when-to-use rule. There is no statement of preconditions, no named alternative for the case where a fact table is not yet linked (project_init), and no exclusion for when not to use it. Guidance is implied at best.

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