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

Adds real context beyond the annotations: the operation is a save-only write with no delivery side effect, and the underlying endpoint is disclosed. It doesn't mention what happens on duplicate titles or that repeat calls create distinct templates (annotations already mark it non-idempotent), so a little remains uncovered.

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, front-loaded with the WRITE marker and the core action; each sentence carries distinct information (action, side-effect scope, endpoint) with no filler.

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 3-parameter creation tool with full schema coverage and no output schema, this covers what the tool does and its key non-behavior (no sending). It stops short of saying what comes back (e.g. a template id for later get_template calls), which would help an agent chain the next step.

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% and the schema already states that at least one of bodyHtml or bodyText is required. The description's 'from HTML and/or text' only restates that constraint, adding no format, length or title-uniqueness detail.

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 ('create a new email template') plus the accepted inputs (HTML and/or text), and the 'nothing is sent' clause separates it from send/mailing siblings. An agent can distinguish it from get_template and list_templates without opening any 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?

'WRITE: create...' plus 'only saved in the account; nothing is sent' gives a clear context for when this is the right call rather than a send operation. It never names the alternatives (list_templates, get_template, create_mailing), so there is no explicit when-not guidance.

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