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

Annotations cover safety (readOnly, non-destructive, idempotent), but the description adds genuinely new behavioral facts: the output is copy plus a suggested canonical action only, nothing is saved/sent/published/contacted, and no login is required. These negative-scope and auth guarantees are exactly what annotations cannot convey.

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 tight sentences with zero padding: what it produces, what it deliberately does not do, and where to go instead. The non-action guarantee is front-loaded alongside the purpose rather than buried.

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?

No output schema exists, and the description compensates by stating exactly what is returned ('copy and a suggested canonical action'). Combined with the auth-free, no-side-effect guarantee and the sibling routing hint, an agent has everything needed to call this 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 both parameters are already fully documented in the schema, including the enum meaning and the 'framing not destination' clarification. The description only echoes the optional nature of claim_id, adding no syntax or format detail beyond the schema. Baseline 3 applies.

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 artifact ('Draft ... handoff copy'), names the source domain (public Cassie context), and identifies the optional grounding input (claim_id). An agent can distinguish this from siblings like get_verified_recommendation without opening the 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?

Names one alternative explicitly ('Use get_verified_recommendation for reader-fit recommendations') and clarifies that claim_id grounding is optional. It gives clear context for invocation but no explicit when-not conditions beyond the single sibling routing hint.

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