gmail_list

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

With no annotations, the description carries the full burden and does so unusually well: it discloses that the list and row identity are remembered across calls, that a stale index causes a not_found refusal, and that a moved row is looked up nearby. It omits any statement of read-only nature, permissions, or cost of the implicit list re-opening.

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?

The second paragraph is dense with genuinely useful state semantics, but the opening contains an abrupt ellipsis fragment ('... The list and its rows are remembered') and the trailing parenthetical about nearby lookup is wordy. Information is front-loaded reasonably, but the structure reads as patched-together prose.

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?

There is no output schema, so the description should convey what a row contains; it only mentions the 'index' field and says nothing about subject, sender, snippet, or unread state. For a list tool whose return shape drives every subsequent index-based call, that leaves a meaningful gap.

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 limit, start, and folder are already fully documented in the schema, including folder's default of staying on the current list. The description adds no syntax or format beyond restating that a folder may be supplied; baseline 3 applies when the schema does the work.

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 ('List conversations') and scopes it to the current list (folder, label, or search results) or an explicitly named folder, which separates it from actions like gmail_search or gmail_folders. It never names a sibling alternative outright, so differentiation is inferred from the 'current list' framing rather than stated.

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?

It implicitly tells the agent this is the enumeration step whose rows feed gmail.read / gmail.reply / gmail.archive, and it explains the current-list-vs-folder choice. There is no explicit 'use X instead when...' guidance toward gmail_search or gmail_folders, so the when-not side is missing.

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