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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds behavior beyond that: the download link expires in five minutes, and files marked untrustedUpload contain data rather than member instructions — a genuine prompt-injection caveat an agent would otherwise miss.

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 sentences, front-loaded with the core action and return payload, followed by the security caveat. No filler, and the most decision-relevant constraint (untrusted content) is not 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?

No output schema exists, so the description usefully spells out what the response contains and its expiry. It covers safety and returns well; it is only slightly thin on access requirements or error behavior for a missing/inaccessible fileId.

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%, with fileId, person, and project all documented in the schema itself. The description adds nothing about parameter behavior (e.g., what happens when person/project are omitted), 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?

States a specific verb and resource (open a file) and enumerates exactly what comes back: details, transcript or extracted text, and a time-limited download link. That return-content framing distinguishes it from siblings like storage_search_google_drive or storage_list_files without needing to name 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?

The 'untrustedUpload' sentence gives real guidance on how to treat returned text, which is a usage rule. But there is no explicit when-to-use-this-vs-alternatives statement — nothing says to prefer this over storage_read_google_drive_file or storage_search_google_drive when looking for file content.

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