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

Goes well beyond the readOnly/openWorld annotations: it discloses the permission model (no results from ungranted sources, body text only with read_body) and the truncation contract with an instruction not to present the count as a total. That is exactly the kind of behavior an agent cannot infer from structured fields.

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: capability and return fields first, then permission scoping, then the truncation caveat. The example is embedded parenthetically and no sentence is redundant.

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?

An output schema exists, so the description needn't explain returns, and the permission/truncation model is covered. The remaining gap is the unspecified paging/filter parameters (maxResults, companyId, connectionId) for a tool with five params and low schema documentation.

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 only 20%, and the description compensates for just two of five parameters: the query format (Gmail syntax plus example) and agentName's authorization role. It says nothing about companyId, connectionId (whose schema text is only 'UUID value wrapper'), or maxResults and its interaction with `truncated`.

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 ('searches the company's connected mailbox') and enumerates the return shape (who, to whom, subject, snippet, when). It separates itself from the write sibling with 'never sends' and from thread-level siblings by scoping to message metadata.

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 concrete usage context: Gmail-style query syntax with a worked example and the requirement to pass your agent_name. It does not explicitly name alternatives (e.g. connection_get_connected_thread for full threads, connection_search_connected_pages for other sources), so routing is implied rather than spelled out.

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