browser_verify_fix

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

With no annotations, the description carries full burden. It outlines the flow (record, execute, verify, compare, return) and mentions return fields. However, it lacks details on side effects, error handling, or failure scenarios, which is a gap for a mutation tool.

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 short and front-loaded with purpose, listing return fields. It is efficient but could be slightly more structured with bullet points for readability. No waste sentences.

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 5 parameters (1 required, enum, nested object) and no output schema, the description covers the tool's flow and return values well. It compensates for the lack of output schema by listing before/after, fixStatus, etc. Reasonably complete for a repair-verification tool.

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 baseline is 3. The description does not add significant meaning beyond the schema, which already describes all parameters well. It mentions the default fixAction but no additional semantic 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 it is a 'repair verification closed-loop tool' that records pre-state, executes repair actions, verifies post-state, and compares differences. It distinguishes itself from sibling tools like browser_click or browser_quick_fix by integrating repair with verification.

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 clear context for usage, listing supported repair actions (click, type, wait, etc.) and the default action (quick_fix). However, it does not explicitly state when not to use this tool or suggest alternatives, such as directly using browser_click or browser_quick_fix.

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