Fetch recent Gmail messages

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

No annotations are supplied, so the description carries the full burden. It discloses the safe-read nature implicitly via 'Fetch', the ordering guarantee (newest first), and — most usefully — that the payload is deliberately partial (metadata + snippet, not full bodies), which tells the agent what it will and won't see. It stops short of stating read-only status explicitly, permission/auth requirements, rate limits, or how results behave when more than maxResults match, leaving some gaps for a no-annotation tool.

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 sentences, zero filler, and the highest-value information (what it returns and its scope vs. gmail_get_message) is front-loaded. Each sentence changes how an agent would use the tool.

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?

With no output schema, the description correctly compensates by enumerating the returned fields (id, from, subject, date, snippet, labelIds, attachment flag). What's missing is behavior when the result set exceeds maxResults (pagination/truncation) and how hours and query combine, but for a triage-oriented reader the definition is nearly self-sufficient.

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% — hours, query, and maxResults all carry their own descriptions and bounds — so the schema already does the heavy lifting and 3 is the correct baseline. The description adds only the 'newest first' ordering constraint, which is not attached to any specific parameter.

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 (fetch) and resource (recent Gmail messages) plus the payload shape (metadata + snippet, newest first) and the intent (triage). It also distinguishes itself from the sibling gmail_get_message by naming the escalation condition, so an agent can pick between them without opening either schema.

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?

Explicitly scopes itself to triage and names the alternative ('Use gmail_get_message when the snippet is not enough to judge a message'), giving both the when-to-use and the when-to-escalate condition. This is the exact kind of routing guidance the dimension rewards.

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