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

Goes well past the annotations: discloses the reward side effect of qualified/approved, that denied halts rewards, that partial updates only touch passed fields, and the endpoint used. destructiveHint/idempotentHint are already declared, and the description adds the concrete financial consequence the agent must reason about.

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 front-loaded with the write marker and the highest-risk information (reward triggering and user confirmation) before lookup mechanics. No filler.

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?

Covers safety profile, side effects, partial-update semantics and record lookup for a 10-parameter mutation with no output schema. Minor gap: nothing about invalid status transitions or what the response confirms.

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 100%, so the baseline is 3. The description adds lookup semantics (referral_id preferred, or external_id/email paired with program_id/program_name) and the partial-update rule, but leaves per-field meaning (note vs public_note, amount for percentage rewards) entirely to the schema.

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 resource ('changes the status, amount or notes of an existing referral') and leads with a 'WRITE:' marker that separates it from the read-oriented siblings (get_referral, list_referrals) and from create_referral.

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?

Explicitly warns that qualified/approved transitions can trigger payouts and instructs 'confirm with the user first', which is a real usage gate. It stops short of naming alternatives (e.g. use create_referral to make a new one), so it is clear context without full sibling routing.

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