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

Annotations only say readOnlyHint=false, destructiveHint=false, offering little about the tool's behavior. The description compensates fully by disclosing that 'Nothing is sent by this tool', the message only leaves CaseMagic after user confirmation, and the link expires. These are crucial behavioral details an agent needs to manage user expectations correctly.

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 sentences with zero waste: the first states the core action and output, the second gives explicit usage context, and the third warns about the send flow and user confirmation. The most important caveat is placed prominently, and every sentence earns its place.

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 tool with 5 simple parameters, no output schema, and sparse annotations, the description adequately covers the key operational details: it creates a draft, returns an expiring link, requires user confirmation, and instructs the agent to tell the user. It doesn't mention potential errors or edge cases, but for this level of complexity, what's missing is minor.

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 all five parameters are already documented with definitions. The description does add the concept that the message is 'from a saved case's address', which gives context to matter_id, but it does not clarify parameter relationships or formatting beyond the schema. Baseline 3 is appropriate because the schema handles the heavy lifting.

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 a specific verb ('Write a CaseMail message'), a resource ('from a saved case's address'), and the outcome ('return a link the user opens to review and send it'). It explicitly distinguishes this from sibling tools like get_case_mail by focusing on writing/drafting rather than reading. The title 'Draft a CaseMail message for approval' reinforces the intended use.

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 gives explicit when-to-use guidance: 'Use when the user asks you to reply to case correspondence or to write to someone about the case.' It also includes a critical caveat that no sending occurs and instructs the agent to tell the user about the confirmation step. However, it does not explicitly name alternatives or state when not to use this tool, so it falls slightly short of the full 5.

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