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

Annotations already declare non-readOnly, non-destructive, non-idempotent, closed-world behavior, but the description adds real value by disclosing that no email is dispatched, that the draft surfaces in the Drafts folder of Relaticle, that signatures are auto-appended, and that raw HTML is escaped. It does not mention duplicate-draft behavior or any permission requirements, which keeps it from a 5.

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 short sentences, no filler, and the most important fact for an agent's decision (nothing is sent) is placed immediately after the purpose statement. Each sentence carries distinct operational 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 an output schema present, return values need not be explained, and the description covers the mutation's real-world effect, content format, and signature default for an eight-parameter tool. What remains thin is the relationship to the update/send/delete draft siblings, which an agent must work out from names.

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 schema already documents all eight parameters including the markdown/HTML-escape rule, the 255-character subject limit, and the signature default. The description's body-format and signature notes largely restate the schema, which is the expected baseline-3 case rather than added semantics.

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 ('Save an email draft') plus the scope ('one of the current user's mailboxes'), and the phrase 'Nothing is sent' implicitly separates it from send-email-tool and send-email-draft-tool. It stops short of naming those siblings or the update/delete draft tools, so an agent still has to infer the boundary from tool names alone.

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?

'Nothing is sent: the user reviews and sends it from Drafts' implies when this is preferable to a send tool, but the when-to-use is left implicit rather than stated as a condition ('use when the user wants to prepare but not send'). No prerequisites are called out in prose, though the schema field for connected_account_id points at the list email accounts tool.

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