mailroom_accounts

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

Annotations already declare readOnly/idempotent/non-destructive, so the baseline is lower. The description adds the useful 'Never returns secrets' guarantee and hints at return content ('transport and health'), but omits auth requirements, rate limits, or pagination behavior.

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 short sentences, front-loaded with the primary purpose and a separate security note. No wasted text; each sentence carries information.

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 read-only listing with annotations carrying the safety profile, no output schema, and fully covered params, the description is nearly sufficient. It signals returned attributes (transport, health) but stops short of describing the full result shape.

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% and both parameters (detail, account) are well documented there. The description only echoes that transport/health are shown, marginally reinforcing detail; it adds little meaning beyond the schema, so baseline 3 is appropriate.

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 every mailbox connected to Mailroom' and enumerates the supported transports (Gmail, IMAP, Microsoft 365) plus the returned health data. It is clearly distinct from sibling mailroom_search/read/send, but it does not explicitly name a sibling or contrast with one, keeping it just below a 5.

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?

Usage is only implied—an agent can infer this lists connected accounts, but the description gives no explicit when-to-use, when-not, or recommendation to call it before mailroom_read/mailroom_search to resolve an account. No guidance on when to enable detail.

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