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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the mutation nature is known. The description adds valuable context beyond annotations: it clarifies the operation applies only to scheduled (unsent) notification emails and that sent messages cannot be changed. This helps set expectations about the tool's limitations without contradicting the annotations.

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?

The description is a single, compact sentence that front-loads the verb, resource, and fields, and includes a crucial constraint (sent messages cannot be changed). There is no waste or redundancy; every word contributes to understanding the tool's purpose and limitations.

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 an update tool with no output schema and moderate parameter descriptions, the description covers the essential points: what is updated, the three fields involved, and the key constraint on sent messages. It does not detail return values or errors, but that is not expected given no output schema. It is sufficiently complete for an agent to call it correctly, though it could mention that scheduled_at is optional to keep current schedule, but that appears in the schema.

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 50% (body and scheduled_at have descriptions; id and subject do not). The description mentions the updatable fields (subject, body, send time) which maps to three of the four parameters, adding some context to underscripted ones. However, it does not provide additional syntax or constraints beyond what the schema already describes, so it only partially compensates for the coverage gap.

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 description states the specific verb 'Update', the resource 'scheduled notification email', and the exact fields affected (subject, body, send time). It also distinguishes from siblings by focusing on scheduled notification emails and explicitly noting that sent messages cannot be changed, which is a differentiator from generic update tools like hires_update_message.

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 usage context by stating 'scheduled notification email' and 'sent messages cannot be changed', which tells the agent when NOT to use it (sent messages). However, it does not explicitly name alternative tools or provide explicit when-to/when-not-to conditions beyond that constraint. The guidance is implicit rather than direct.

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