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

Annotations already declare the read-only, non-destructive, idempotent safety profile, so the description's job is supplemental. It adds two useful behavioral facts: it operates on the *live* shared frame rather than arbitrary images, and it returns a natural-language answer (relevant because there is no output schema). It does not mention latency, cost, or what happens if no share is active, so it stops short of a 5.

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 short sentences, each earning its place: purpose, return value, then the usage restriction. The most decision-relevant constraint is front-loaded alongside the purpose rather than buried.

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, the description correctly explains the return value, and the annotations cover safety, so the tool is callable as described. The only gap is the slight tension between 'look at the screen currently being shared' and the optional image_b64 frame parameter, which the description never reconciles for the caller.

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 the schema already documents all three parameters and the baseline of 3 applies. The description only restates the question semantics already present in the schema and adds no format, syntax, or constraint detail for question, image_b64, or in_workspace.

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 verb ('Look at') and resource ('the screen currently being shared in a meeting') plus the action taken ('answer a question about it'). This clearly separates it from the screenshot/vision siblings (android_screenshot, browser_take_screenshot) which capture rather than interpret a live screen-share. An agent can identify it without opening the 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 positive trigger ('explicitly asks about the screen/slide/document being shown') and an explicit exclusion ('ONLY when'), which is the strongest form of routing guidance in the corpus. Nothing about when to prefer this over a plain screenshot or web_fetch is left to inference.

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