Upload Files and Ask Gemini

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and non-idempotent, so the safety profile is covered. The description adds the useful fact that files leave the local machine for Gemini, but omits whether uploads persist across turns, whether the chat window is shared with gemini_chat, and what a repeated call does to an existing session.

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 front-loaded sentence with no filler, and the verb+resource comes first. It is arguably too terse for a six-parameter, session-affecting tool, but nothing in it is redundant.

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 non-read-only, open-world tool with six parameters and chat-session state (model, thinking_level, new_chat, timeout), one sentence leaves key questions unanswered: does the upload persist in the conversation, and how does this differ from gemini_chat plus gemini_new_chat. High schema coverage offsets some of this, but the session semantics are not in the schema at all.

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 all six parameters are already documented, setting the baseline at 3. The description adds only a mild hint about supported file kinds (images, documents, code); it says nothing about model selection, thinking_level, timeout behavior, or what new_chat actually resets.

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 compound action: uploading local files (images, documents, code) to Gemini and asking a question about them. This implicitly distinguishes it from gemini_chat (no file upload), but the description never names that sibling or explicitly contrasts the two.

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?

Usage is only implied by the file-upload framing — an agent can infer 'use when I have local files to reason about.' There is no explicit guidance on when to prefer gemini_chat instead, nor on how this interacts with gemini_new_chat or gemini_switch_model.

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