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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description reinforces this ('updates the existing template rather than failing'). Beyond that it discloses non-obvious behavior: Mustache interpolation with HTML-escaped {{value}} vs raw {{{value}}}, per-channel required fields, and the WhatsApp/Meta pre-approval constraint that refuses arbitrary composed bodies.

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?

Four tight paragraphs, each doing distinct work (rendering semantics, keying/upsert, per-channel requirements, defaults). Dense and front-loaded, though the WhatsApp rationale could be trimmed slightly without losing meaning.

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 9-parameter setter with no output schema, the description covers what an agent needs: rendering rules, upsert semantics, per-channel field requirements, and interaction with platform defaults. Return values are not needed since annotations confirm a safe, idempotent write.

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 89% (baseline 3), but the description adds conditional meaning the schema's flat per-field docs cannot express: email needs subject+body_text with body_html optional, slack/in_app need body_text, and whatsapp requires provider_config.templateName. This goes beyond the schema's field-level descriptions.

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?

The opening sentence states a specific verb and resource ('Set the message a notification sends') and immediately scopes it to per-send Mustache rendering. An agent can distinguish this from set_notification_channel, list_notification_templates, and delete_notification_template 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?

It gives clear context: templates are keyed per (key, channel_type), calling again updates rather than fails, and templates override shipped auth defaults. However it never explicitly names a sibling alternative or a when-not condition (e.g. when to configure the channel first), so it falls short of full routing guidance.

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