Start an annotation session

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

With no annotations, the description carries the full burden and does disclose two important traits: it is user-visible (opens a window with an overlay, a visible side effect) and it is asynchronous (returns immediately, requires polling). It omits cleanup/teardown behavior (whether stage_close ends the session) and what happens if a session is already active, so not fully transparent.

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?

Two tightly packed sentences: the action comes first, then the asynchronous follow-up. No filler, no restatement of the title, and every clause carries information.

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, so the description should indicate what the call returns to make the polling instruction actionable (e.g., a session id or status token) — it does not. Cleanup/termination and required parameter meaning are also missing. It is adequate for the happy path but leaves gaps for a stateful UI side-effecting 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 description coverage is 0% across three parameters (url, width, height), and the description mentions none of them. An agent gets no explanation of what url refers to (the app page to overlay?) or what units/conventions width and height follow, so the description does not compensate for the schema gap.

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 concrete action and outcome: opens a visible window with a drawing overlay for the user to mark parts of the app and attach notes. That is clearly an annotation-session starter, distinct from read-only siblings like annotations_list or annotations_get. It does not explicitly contrast with stage_open, which also opens a visible window, leaving a small ambiguity for an agent choosing between them.

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?

Gives explicit lifecycle guidance: the call returns immediately and the agent should poll annotations_list until status is ready. That is a real when/how-to-use instruction pointing at a named sibling. It lacks any exclusion or precondition (e.g., what to do if a session already exists), so it stops short of full routing guidance.

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