loom_explain

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

With no annotations provided, the description takes on the full burden. It transparently discloses the output format (plain text), the content scope (ADR grounding, F-number references, execution-time values), and the return envelope (ok=true with text, ok=false with M-code diagnostics). This covers key behavioral traits, though it stops short of stating side-effects or permission needs, which are likely immaterial for an explain operation.

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 efficient: the first sentence states the core purpose, and the second adds key output characteristics and error behavior. No wasted words or redundant restatements of the tool name. A slight lack of structured details about parameters keeps it from a perfect score, but it remains compact and readable.

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?

The description provides a solid overview of what the tool does and what the output contains, and the output schema likely covers return details. However, it does not explain the optional variables parameter, nor does it clarify whether the manifest must be pre-compiled or if the tool compiles it on the fly. These gaps leave the description incomplete for a tool with two parameters and a complex explanation output.

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 0%, so the description must compensate for parameter meaning. It mentions the manifest ('for a manifest') but does not explain the required manifest_path parameter beyond the tool's focus, and it completely omits the optional 'variables' parameter. The description adds minimal value over the raw schema, leaving an important parameter undocumented.

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 a specific action: 'Render `loom explain` for a manifest' – depicting the compiled plan as its own justification. It distinguishes itself from siblings like loom_compile by focusing on explanation and justification rather than compilation, and from iamf_validate/inspect by outputting a walkthrough of every target's routing and step rationale.

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 implies usage context by describing the output ('walks every target', 'why it routed'), suggesting when a user would want to understand plan decisions. However, it does not explicitly state when to use this tool versus alternatives, nor any exclusions or prerequisites, so guidance remains implicit rather than explicit.

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