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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds a genuinely non-obvious semantic: the stored image is retained, so only the library entry is removed. It also adds the human-confirmation requirement, which no annotation conveys. It stops short of saying whether the record deletion itself is reversible or what an error returns.

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 carrying distinct load: what it does, the surprising retention behavior, and the confirmation requirement. Front-loaded with the action, zero redundancy.

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?

For a one-parameter destructive tool with rich annotations and an output schema, the description covers the essentials an agent needs: scope, the retention caveat, and the confirm-first rule. The only gap is irreversibility of the record removal itself.

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% and the single `id` parameter is fully documented in the schema (including its source, list_screenshots/search_screenshots). The description adds nothing about the parameter, so the baseline of 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?

States a specific verb and resource ("Remove a screenshot") plus scope ("from the signed-in user's cloud library"), which cleanly separates it from the read-only siblings (get_screenshot, list_screenshots, search_screenshots) and from rename_screenshot.

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 an explicit precondition — "Ask the user to confirm before calling this tool" — which is exactly the gating rule an agent needs for a destructive call. It does not name an alternative action (e.g., what to do if the user wants to keep the record), so it falls short of full when/when-not guidance.

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