sign_agent_trace

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses side effects: writes an envelope file, uses local identity store, hashing, and no network. This provides substantial behavioral context.

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 concise at five sentences, front-loaded with purpose and usage, followed by side effects and return type. Every sentence adds value without redundancy.

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 presence of an output schema, the description appropriately summarizes the return type. The side effects and no-network behavior are clearly stated. Sibling tools include verification counterparts, providing complete context.

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 coverage is 100%, so the description need not add much. It restates the schema's description for trace_path and mentions the default for save_path, but does not add new syntactic details or constraints that would significantly help the agent.

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 action (sign), resource (browser-agent JSONL trace), and method (Ed25519 identity). It specifies the exact trace format (WEB_WIZARD .traces/<runId>.jsonl), distinguishing from sibling tools like sign_action or sign_mcp_manifest, but could be more explicit about differentiation.

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?

It explicitly states 'Use when a WEB_WIZARD or Steel run completes,' providing contextual triggers. It also notes the absence of network activity. However, it does not mention when not to use the tool or suggest alternatives like verify_agent_trace.

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