debug_get_flow_graph

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions connecting to live sessions and returning JSON or Mermaid format, giving some insight into behavior. However, it does not disclose side effects (likely read-only), permissions, or any potential errors. The disclosure is adequate but not exhaustive for a debug tool that may interact with live sessions.

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

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

The description is a single paragraph with multiple sentences, but the opening sentence about Arch is generic and not directly about this tool. The core purpose is introduced in the second sentence. It's reasonably concise, but not perfectly front-loaded—the key 'get the execution graph' could appear earlier. There's some redundancy with the '[Arch Debug]' prefix and the first sentence.

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

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

Given the tool's moderate complexity (3 optional params, output format choice) and lack of an output schema, the description clarifies what the graph shows and mentions output formats. It doesn't elaborate on the structure of the JSON or Mermaid output, nor does it address limitations or prerequisites (e.g., needing an active session). While not completely detailed, it provides enough for an agent to understand the tool's purpose and basic usage.

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

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

Schema description coverage is 100%, so each parameter already has a description. The tool description adds limited extra meaning—it mentions agent types and output formats, but these are already covered by the schema enum for format and the descriptions for sessionId and includeAppGraph. Baseline of 3 is appropriate since the schema does the heavy lifting and the description adds marginal value.

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

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

The description clearly states the verb 'Get' and the resource 'execution graph', and specifies the scope ('any agent type') and content ('flow steps, tools, handoffs, and routing logic'). It distinguishes itself from siblings like debug_get_current_state or debug_get_span_tree by focusing on graph structure rather than state or spans, though it doesn't explicitly name alternatives.

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

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

The description provides general context about Arch's debugging capabilities (connecting to live sessions, tracing failures, inspecting execution state) but does not explicitly state when to use this tool over its many debug siblings. Usage is implied by the description of the graph content, but there's no direct guidance on choosing between debug_get_flow_graph and debug_get_span_tree, debug_explain_decision, etc.

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