Remind

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

The annotations declare openWorldHint, non-idempotent, non-destructive, but the description adds the crucial behavioral facts: an email is dispatched immediately, it goes to every current signer, and it requires user confirmation. That exceeds what the annotations convey. It still omits failure behavior (what happens if nobody is pending).

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 short sentences, action first, constraint second. Every clause earns its place with no repetition of structured data.

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?

Adequate for a one-parameter tool with annotations, but gaps remain: what happens when no signer is pending, whether repeat sends are blocked (annotations say non-idempotent), and confirmation of what the id refers to. No output schema exists to cover the return behavior.

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 0%, so the description must carry the parameter burden. 'This document' implies the single 'id' parameter is a document identifier, but the description never states that explicitly or notes it is a UUID, leaving that to the schema's format field.

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 gives a specific verb and resource ('E-mails a reminder... on this document') and scopes it to 'everyone whose turn it is', which separates it from send_document and send_from_template. It does not explicitly name a sibling, but the action is distinct enough that an agent can route correctly.

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?

'Confirm with the user first' is a real usage constraint, and 'whose turn it is' implies the precondition. However, no alternatives are named and nothing says when NOT to use it (e.g., when no one is waiting or a reminder was already sent).

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