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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=true, so the safety profile is covered; the description usefully goes beyond that by specifying the return shape (plain text letter, [bracketed] placeholders for missing data, attachment checklist, tips) and asserting it 'never sends or files anything', which is the key side-effect boundary. It stops short of describing how placeholders behave with required-but-absent inputs like the reason/denial_code pairing.

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, no waste: purpose first, then trigger examples, then return contract and side-effect boundary. Information is front-loaded 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?

There is no output schema, and the description compensates by describing the return payload (letter text, placeholders, attachment checklist, tips) as well as the no-send guarantee. For a 14-parameter, zero-required generation tool, the combination of trigger examples, output description, and behavior boundary gives an agent enough to call it correctly.

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 the schema already documents all 14 parameters, including the reason enum values and the denial_code fallback rule. The description adds only indirect signal about parameters via its example phrasings and the bracket-placeholder convention. Baseline 3 is appropriate when the schema carries the semantic load.

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+resource ('Draft an appeal letter') and immediately adds the scope boundary ('for the user to review and send'), which separates it from the sibling read-only lookups (get_appeal_rights, get_appeal_deadlines, explain_denial_code). The title and description align exactly, and an agent can tell this is the generative tool among informational siblings.

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?

Provides two concrete trigger utterances ('my insurer denied my MRI as not medically necessary, help me appeal' and 'write an appeal letter for an out-of-network denial') that map directly to the reason enum, giving clear context for when to invoke. It does not, however, name the sibling tools or state when not to use this one (e.g., when the user only wants deadlines or rights information).

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