Returns the running browser instance for the specified profile.

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

Annotations do not cover error behavior, and the description usefully discloses that the call throws when no instance is running — a genuinely additive detail. However, it says nothing about the error type/message, what the returned instance object contains, or why a getter carries readOnlyHint=false. The annotation/description pairing is odd but not directly contradictory.

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?

A single short sentence with no waste, but it is not front-loaded with the primary behavior — it leads with the exception case and omits the success path entirely, which is the wrong emphasis for a getter.

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?

With no output schema and no annotations describing the return value, the description is the agent's only source for what this call produces, and it is silent on that. Nothing explains the payload shape or how it differs from the sibling list-style browser instance tools.

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 100%, so both profileId and workspaceId (including the -1 default meaning) are already fully documented in the schema. The description adds no parameter-level semantics beyond that, so the baseline 3 applies.

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 only states the failure mode ('Throws if no browser instance is currently running for the given profile') and never says what the tool does on success or what it returns. The actual purpose is carried entirely by the title, and the description does not distinguish this tool from the sibling get_browser_instances (plural).

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?

There is no guidance on when to call this versus get_browser_instances, focus_browser_instance, or start_browser_instance. The only usage signal is implicit: the tool is meant for profiles that already have a browser running, but that is left for the agent to infer.

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