gmail_read

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

With no annotations, the description carries the burden and does disclose the key side effect: opening an unread conversation marks it read unless keep_unread=true. It also reveals UI-level behavior (collapsed messages expanded, thread scrolled, optional stay_open) that no structured field conveys. It omits error/return behavior beyond expect_subject's not_found.

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 paragraphs: what is returned, how the target is selected, then side effects. The targeting rule and the read-marking side effect are both front-loaded and no sentence is 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 an 8-parameter tool with no output schema and no annotations, the description covers targeting, side effects, the fast-path option, and the safety-check failure mode. Gaps remain on the exact return shape (truncation at max_messages) and what happens on index out of range.

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, but the description adds real meaning the schema doesn't: the precedence/interaction among index, query and folder, and the default behavior when index is absent. It still never mentions max_messages or expect_subject.

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 ('Read a whole conversation') and immediately enumerates the payload (subject, labels, every message with from/to/cc/date/body/attachments). It also distinguishes the read-thread scope from list/search tools by explaining that it consumes their row index.

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?

Clearly frames the call as operating on a row from gmail.list / gmail.search or a folder, and covers the no-index case (read the already-open conversation). It stops short of explicitly routing away from a sibling that opens a single message (gmail_open) or a summarizer (gmail_summarize).

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