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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write profile is known. The description adds real behavioral context beyond that: the recipient cannot be redirected, the body is Markdown re-rendered through a template that supplies sign-off and footer, and an object id not in the user's graph 'silently loses its link'. It does not state that sending is immediate and irreversible, which is the one gap for a destructive-hint tool.

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?

Front-loaded with the what and when in the first two sentences, then organized into labeled blocks for formatting and links. It is long for a 2-parameter tool, and a few rendering details could be tightened, but every paragraph carries actionable instruction rather than padding.

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 no output schema, two required params, and a mutation profile, the description covers everything an agent needs: recipient constraints, subject policy, body formatting rules, link resolution and its silent-failure mode, footer ownership, and the draft alternative. Nothing essential to a correct call is missing.

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%, so the baseline is 3, but the description goes well beyond it: it tells the agent to compose a short specific subject if the user gave none, specifies the Markdown subset that renders (subheadings, bullets, bold, quotes, tables), forbids HTML and manual sign-offs, and defines the two link syntaxes including the failure mode of an unknown id.

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 precise verb and resource plus the defining scope constraint: 'Send an email to the signed-in user at their own account email address', and reinforces 'The recipient is fixed to their own address and cannot be changed.' It explicitly separates itself from the near-identical siblings create_gmail_draft and send_outlook_email.

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?

Gives concrete trigger phrases ('email me this', 'send myself a reminder') for when to use it, and names the alternative with the exact condition that selects it ('To write an email to anyone else, use create_gmail_draft instead'). Both when-to-use and when-not-to-use are covered.

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