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

Annotations already cover readOnly, idempotent, and non-destructive, so the bar is lower. The description still adds a genuinely useful trait beyond them: 'Reading does not mark anything read,' which tells the agent there is no read-status side effect. It stops short of describing result shape 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?

Terse and front-loaded: the core verb leads and the three action clauses follow in a single compact span with no filler. The dense parenthetical phrasing is slightly cryptic on first read but every clause 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?

With 8 parameters, no output schema, and one required field, the description covers what each action does and the key non-side-effect trait. Because there is no output schema, the return shape (thread list fields, pagination cursor `next_before`) is only partially conveyed through the schema's `before` description, leaving a small gap.

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 88%, so baseline is 3, but the description earns more by mapping each enum value of `action` to a distinct meaning and clarifying that `messageId` returns one full body versus `threadKey` returning the thread's messages. The action values themselves carry no per-value description in the schema, so this is real added value.

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 the verb (read) and resource (email), then enumerates the three concrete actions with their scopes: threads = inbox list, thread = a thread's messages or one full body, accounts = mailboxes and send-as addresses. This lets an agent distinguish the tool from email_send and email_thread_update without opening the schema. It does not explicitly name a competing sibling for read-like operations, which keeps 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?

The description implies when each action is appropriate (threads for listing, thread for a conversation, accounts for send-as addresses) and the schema adds 'only when the snippet is not enough' for messageId. However, there are no explicit when-not rules or named alternatives among the read siblings, so usage must be inferred from the action enumeration.

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