browser_analyze_run

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

The description discloses key behavioral traits: it scans the whole run (not just last action), categorizes failures with specific labels, and surfaces the earliest with causal explanation. No annotations are provided, so the description carries the full burden; it does a good job but doesn't explicitly state whether the tool is read-only or has side effects.

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 front-loaded with 'FIRST POINT OF FAILURE' and each sentence adds value: scope, categories, causal explanation, session context. It could be slightly more concise but is not overly verbose.

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 explains the tool's behavior and context (loaded or live session), but without an output schema, it lacks explicit detail about the return format (e.g., a list of errors, an object with the first failure). This leaves some ambiguity for an AI agent.

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?

The input schema has no parameters, and schema description coverage is 100% (0 of 0 params documented). Per guidelines, baseline is 4 when there are 0 parameters, and the description adds no param info because none is needed.

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?

Description clearly states the tool scans the entire recorded run for failures, labels them with error categories, and surfaces the earliest one with a causal explanation. This distinctively separates it from sibling tools like browser_verify (which checks live state) or browser_explain_last_action (focuses on last action only).

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 positions this as the 'FIRST POINT OF FAILURE' and explains it operates on a loaded past session or live session. This implies it's the go-to for diagnosing failures after a run, but doesn't explicitly mention when to avoid using it or direct alternatives among siblings.

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