gmail_gemini

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

No annotations are provided, so the description carries the burden, and it does disclose real behavior: the conversation is opened first as a side effect, a timeout bounds the wait, and a specific error (gemini_unavailable) is raised when the account lacks Gemini. It stops short of saying whether asking is purely read-only or whether the opened conversation changes UI state that later tools depend on.

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 tight sentences, front-loaded with the core action, then the mode split, then the failure mode. No restatement of the name, no filler.

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 6-parameter tool with no annotations and no output schema, the description covers the action, both invocation modes, the return value ('answer text'), and the key error. It is slightly thin on the interaction between timeout expiry and the returned result, and on the expect_subject mismatch case.

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 coverage is 100%, so the baseline is 3; the description earns a bump by explaining the group-level interaction — that index/query/folder act together to pre-open a conversation and that omitting all three selects mailbox scope — which the per-field schema text does not state. It does not explain expect_subject's failure behavior or what happens when the safety check fails.

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 ('Ask Gemini in Gmail and return its answer text') and splits the tool into two clearly described modes (mailbox-level vs. conversation-level). It does not, however, address the closest sibling, gmail_summarize, so an agent must infer which of the two LLM-style tools to pick.

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 conditional routing: omit index/query/folder to ask about the mailbox, supply them to ask about a specific conversation, with a concrete example question. It lacks any when-not guidance or named alternative (e.g. gmail_summarize, gmail_search), so the routing is clear internally but not against siblings.

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