browser_guide

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

With no annotations, the description carries the full burden, and it delivers real behavioral context: relative size of each topic ('short' for start, 'all = every command, about 25,000 tokens') so the agent can budget context, plus the one-shot call cadence. It stops short of stating the tool is side-effect-free/read-only, which would fully close the gap.

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?

Three dense sentences with the primary instruction front-loaded and each topic clause carrying distinct information. The opening 'written for you' is mild filler, but no clause is truly redundant for a tool whose whole purpose is disambiguation.

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?

There is no output schema and no annotations, and the description compensates by describing the content and rough size of each topic, which is what the agent needs to choose one. A note on how the guide is returned (single string vs. structured) is the only missing piece.

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 entirely, and it does: it defines all three topic values (start, commands, gomini), enumerates the group sections (open, read, act, batch, accounts, person, browser, all), and explains that query takes words like "selector click" to match commands. This is meaning well beyond the raw enum lists.

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 artifact ('how to use this browser') and its role as a documentation entry point, which cleanly separates it from the ten action siblings (browser_open, browser_read, browser_act, etc.). An agent can tell this is the meta/help tool without opening any schema.

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 gives an explicit ordering rule ('Call it once before your first browser action') and then routes within itself: topic=start is labeled 'read this first', topic=commands is for finding commands, topic=gomini for the local model. When-to-call and which-topic-to-pick are both spelled out.

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