gmail_mark_read

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

No annotations are provided, so the description carries the full burden. It does disclose one useful behavioral trait — that unchanged conversations yield changed=false rather than an error, implying idempotency — but says nothing about permissions, scope of effect, or what a bulk 'all' action does to the mailbox.

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 tight sentence with the key outcome hint parenthesized, front-loaded and free of waste. It is arguably under-specified rather than verbose, but nothing in it 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 a mutation tool with seven parameters and no annotations or output schema, the description is thin — it never explains that conversations must first be selected via list/search results. The fully documented schema compensates enough that an agent can still call it, but the mental model must be assembled from parameter descriptions.

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 seven selection parameters (all, index, indexes, match, query, folder, max_rows) are fully documented in the schema; baseline 3 applies. The description adds no meaning about how these selectors combine or which row source they draw from.

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 ("Mark conversations as read"), which is clear enough to act on. However it does not distinguish itself from nearby siblings like gmail_mark_unread, or from gmail_read (which opens a message), so the agent must rely on the tool name alone for that distinction.

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?

No guidance on when to use this versus gmail_read, gmail_mark_unread, or gmail_read/scroll for reading mail. There are no stated preconditions tying it to a prior gmail_list or gmail_search selection, even though the parameters are all row-selection based.

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