analyze_visual_evidence

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

With no annotations provided, the description carries the full burden, and it does so well. It discloses that the tool runs no vision model, returns images unchanged, redacts evidence, and focuses on failed/slow requests. This prevents false expectations about image analysis.

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 compact and front-loaded. The first sentence states the core function, and the second paragraph adds a necessary and behaviorally important caveat. Every sentence earns its place without filler.

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 covers the core behavior and a major misuse case clearly. The main gap is that it does not explain how an agent should supply HAR data via har_json versus har_path, or what the context parameter is for.

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%, and the description partially compensates: it explains image_base64's echo-only behavior and implies slow_threshold_ms relates to slow requests. However, the roles of context, har_json, and har_path are left implicit, relying on parameter names alone.

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 states a specific action and resource: extract structured evidence from a HAR / browser network-tab export, listing failed and slow requests, correlation headers, and redaction. It also corrects the misleading 'visual' in the tool name by explicitly saying it runs no vision model.

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 gives explicit when-to-use guidance: use it to extract HAR-based evidence, and explicitly warns against passing a screenshot the model already has. It also explains the only case where image_base64 should be passed, which is clear usage guidance.

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