Skip to main content
Glama

ecosystem_apply_architecture_md

Submits architecture markdown for deep review or records a failure reason, advancing the workflow stage and enabling manual retry when needed.

Instructions

Stage 1 writeback — submit architecture_md OR report failure.

Success path (default): pass non-empty architecture_md (800-1500 words Chinese markdown). The OS persists it, advances stage_status -> architecture_done, and marks the deep_review row completed.

Failure path: leave architecture_md empty and pass error_message; the OS advances stage_status -> architecture_failed so manual retry surfaces in the UI.

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": {
      "deep_review_id": "<deep_review_id>"
    },
    "name": "ecosystem_apply_architecture_md"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idNoOptional agent identifier recorded on the review row.
error_messageNoShort message stored on review.risks_md (failure path).
deep_review_idYesTarget deep_review row id.
architecture_mdNo800-1500 words of English markdown (success path).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.11.2

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and largely meets it: it discloses concrete mutations ('persists it', 'advances stage_status -> architecture_done', 'marks the deep_review row completed') and the corresponding failure transition, plus the non-obvious detail that error_message is stored on risks_md. It omits idempotency/retry behavior and whether a row already in architecture_done can be overwritten, which matter for a state-mutating writeback.

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 lead clause front-loads the identity and the two paths are labeled with bolding plus an explicit '(default)' marker, so an agent can scan to the branch it needs. It is slightly longer than necessary, since the state transitions are restated in both the description and implied by the schema defaults, but no sentence is pure filler.

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

Completeness4/5

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 the description covers the two operational paths and their side effects. What is missing is behavior for ambiguous invocations (both fields populated, a too-short or too-long body, a row not in the expected stage) and the language discrepancy that directly affects how the required field must be produced.

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 100%, so the parameters are already documented and the description mostly restates them. It introduces a direct conflict about input language — description says 'Chinese markdown' while the schema property says 'English markdown' — which is a real ambiguity an agent must resolve before writing 800-1500 words of content. The error_message and agent_id semantics add nothing beyond the schema.

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 clause names a specific verb and resource ('Stage 1 writeback — submit architecture_md'), and the 'Stage 1' framing plus the architecture_md artifact implicitly separates it from the other ecosystem_apply_* stage tools. It stops short of naming a sibling to route against, but an agent can tell what artifact this tool writes and at which stage.

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

Usage Guidelines4/5

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

It clearly states the default success path and the explicit condition that selects the failure path ('leave architecture_md empty and pass error_message'), which is exactly the branch decision an agent must make. It offers no guidance relative to alternative tools (e.g. how it differs from ecosystem_apply_quality_review), and does not say what to do if both fields are supplied or neither path is intended.

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