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

Annotations declare readOnly=false, idempotent=false, destructive=false, so safety profile is partly covered, but the description adds real value beyond them: reminder credits may be consumed, delivery is single-shot, and refreshing without progress should not re-trigger. It stops short of describing delivery failures or credit units, but the cost and non-idempotency reinforcement are meaningful context.

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?

Two tight sentences with zero filler; the action and its scope are front-loaded before the precondition and the cost warning. Every clause carries operational weight.

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 non-idempotent, credit-consuming notification with no output schema, the description supplies the precondition, cost awareness, and anti-repeat rule an agent needs. It does not mention what a successful send returns or how to detect delivery failure, a modest gap.

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 each of the four parameters is already documented by the schema; the description adds only the 'pending signer in active step' scoping for signer_id. It says nothing about estimate_only, but the schema covers it, so the baseline of 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+resource+scope: 'Send one reminder to a pending signer in the assignment's active step.' The 'one reminder' and 'active step' qualifiers make it distinguishable from sibling send/notify tools like assinafy_send_pdf_for_signature. An agent can identify the action 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?

Gives an explicit precondition ('after confirming with assinafy_get_document that they have not signed'), naming the exact sibling to call first. It also provides a when-not rule: 'never repeat a reminder only because progress is unchanged,' which prevents a common misuse loop.

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