connector_gmail_searchSearch Gmail messages using natural-language queries and return matching results, so you can locate specific emails for review, follow-up, or reference.
Search Gmail. Search, read, send, and manage Gmail messages.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return | |
| query | Yes | Natural-language search query |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the description is not the primary carrier of the safety signal. However, it adds nothing about why a search would be destructive, what data could be affected, or any auth/rate-limit behavior, and its read-flavored "Search Gmail" framing sits in tension with the destructive annotation without resolving it.
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?
It is short and front-loads the core action, which is good. But the second sentence is connector-family boilerplate that does not describe this tool and does not earn its place – it costs clarity rather than buying any.
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 simple two-parameter search with full schema coverage and no output schema, the description only needs to pin down scope and the sibling relationship. Instead it overclaims write capabilities, never notes that results are message listings (vs. connector_gmail_fetch for full content), and leaves the destructive annotation unexplained.
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% – both `query` ("Natural-language search query") and `limit` ("Maximum number of results to return") are fully documented in the schema. The description contributes no additional syntax, default, or format detail, so the baseline 3 applies.
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?
The first sentence gives a clear verb+resource ("Search Gmail"), but it is immediately diluted by "Search, read, send, and manage Gmail messages," which advertises capabilities this tool's schema (query + limit only) cannot perform. It also makes no attempt to distinguish itself from the close siblings connector_gmail_fetch and connector_gmail_act, so an agent cannot tell from the text which Gmail tool to pick.
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?
There is no statement of when to use this search tool versus connector_gmail_fetch (retrieving message content) or connector_gmail_act (mutating Gmail). The only guidance is an implicit "search" verb, and the trailing sentence actively suggests the tool also sends and manages mail, which steers agents toward the wrong sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.