Open a stage

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

With no annotations, the description carries the full behavioral burden and does reveal two real traits: the window is parked off-screen by default and a stage_id is returned. It omits whether multiple stages can coexist, what a well-formed vs. rejectable URL looks like, error behavior, and whether the caller must eventually close the stage, leaving meaningful gaps for a stateful browser 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?

Four short sentences, front-loaded with the core action and its side effect, then the return value. There is no filler; the final 'Does not choose what to test' line is slightly cryptic but still earns its place as a scope disclaimer.

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?

No output schema exists, and the description compensates by naming the returned stage_id. For a single-required-parameter setup tool, the remaining omissions (errors, multi-stage concurrency) are minor enough that an agent can call this correctly.

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 url, width, height, and hidden are all documented with defaults and bounds in the schema itself. The description only echoes the hidden parameter's effect ('parked off-screen unless hidden=false') without adding format, interaction, or edge-case detail beyond what the schema already says.

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?

States a specific verb and resource ('Open a URL in a real browser window') and adds an ownership scope ('owned by this server'), which separates it from generic browsing. The closing line 'Does not choose what to test' distinguishes it from orchestration siblings like scenario_run, though no sibling is named outright.

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?

'Does not choose what to test' implies this is a low-level setup primitive rather than a test driver, which is useful directional guidance. However, it never states when to call this versus stage_focus, stage_state, or scenario_run, nor any preconditions such as pairing with stage_close for cleanup.

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