browser_cmd

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

With no annotations, the description carries the behavioral disclosure burden. It does reveal that the tool accepts 'raw administrator input' and can run 'ANY agent-browser command,' which implies broad execution capability. But it does not explicitly mention potential side effects, error modes, or the impact on the stealth session, leaving some uncertainty.

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 uses labeled sections (Purpose, Constraints, Example) which makes it scannable and front-loaded. Each part is useful, though the 'COMPLETE browser…' phrase is somewhat vague and the ellipses suggest incomplete content.

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 clear purpose, a prerequisite, and an example, which is good for a complex escape-hatch tool. However, it leaves 'json' and 'timeout' semantics undocumented and does not address error behavior or side effects. The presence of an output schema reduces the need to describe return values, but the parameter gaps keep it from being fully complete.

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. It defines 'args' as raw administrator input and the example shows 'session' usage, but 'json' and 'timeout' are not explained at all. The description adds some value for the required parameter but leaves most parameters underspecified.

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 'runs ANY agent-browser command against the current stealth session,' which is a specific verb+resource+scope. It also self-identifies as an 'escape hatch' for features absent from structured tools, distinguishing it from siblings like browser_open and browser_act.

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 frames the tool as an escape hatch for 'controller features absent from structured tools,' which tells the agent when to use it over alternatives. It also states a mandatory prerequisite: 'Call browser_skill(name='core', full=True) first.' However, it does not provide explicit exclusions or directly name which structured tool to prefer for simpler cases.

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