search_all_accounts

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

Annotations already carry readOnlyHint and openWorldHint, but the description adds two things they don't: results are grouped per account, and the output arrives wrapped as UNTRUSTED third-party data that must not be treated as instructions. That injection-safety warning is real behavioral value. It stops short of covering failure modes (no connected accounts, auth errors) or result ordering.

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?

Two sentences, both front-loaded: the operation and its cross-account scope come first, then the safety caveat. No filler, no restatement of the tool name.

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 only two fully documented parameters and no output schema, the definition covers what an agent needs to call it correctly, including the untrusted-result handling. The remaining gap is edge-case behavior (empty account set, partial failures across accounts), which is minor for a read-only search.

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%, so the baseline is 3; the description slightly exceeds it by framing 'query' as a Gmail search query and implying results are capped per account via max_per_account. It adds no syntax examples or default behavior beyond what the schema already spells out.

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 (searches) plus resource (Gmail messages) and a scope qualifier ('across every connected account') that separates it from the single-account search_emails sibling. It also says results are grouped by account, so the agent knows the shape of the answer before opening the 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?

'Across every connected account' implies when to pick this over search_emails, but the description never states the condition explicitly or names the alternative. There is no guidance on what to do when zero accounts are connected (check_accounts/connect_account exist), so the routing is left to inference.

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