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

Goes well beyond the annotations by disclosing atomicity ('all or nothing'), specific error codes (limit_exceeded, invalid_payload) and what each means, the 20-slot account limit, the 180-day ceiling, and instant application. Annotations only mark it non-read-only, so this carries real operational detail.

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?

Front-loads purpose, then parameters, then error behavior in three dense sentences with no filler. Every clause (limits, error names, atomicity) 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?

For a nested-object batch mutation with an output schema, the description covers everything an agent needs: batching rules, per-entry fields, failure semantics, and limits. Failure modes are the key gap an output schema wouldn't convey, and they are fully addressed.

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?

The schema documents fire_at_local and text, but the description adds value by explaining the user's wall-clock convention, that text is delivered verbatim, and the validation rules (past time, >180 days ahead, empty text) that live nowhere in the schema. Some overlap with schema text keeps it from a 5.

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 ('Schedule several reminders'), gives scope ('up to 20 per call'), and characterizes the intended use ('one thing spread over several dates'), which cleanly distinguishes it from the singular sibling create_reminder. An agent can pick between the two without opening a 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?

The description explains the batch context for using this over the single-reminder tool and explicitly routes the agent to cancel_reminder when reminder slots need freeing. It stops short of an explicit 'use create_reminder instead when scheduling one' statement, so it's clear context but not a full when/when-not rule set.

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