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

Annotations only flag a destructive, non-read-only write; the description goes well beyond them by disclosing the concrete side effects (immediate enrollment, prerequisites skipped, access period applied, emails sent), the idempotency semantics, and the non-reversal of a rejection. These are the high-value operational facts an agent must know before invoking a destructive tool.

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?

Four dense sentences, front-loaded with the action and its irreversible consequence, then sibling routing, then the return shape. Nothing is padding; each clause carries a distinct fact.

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?

Despite there being no output schema, the description states the return shape {id, status, decisionNote, reviewedAt} and covers the edge cases (repeat decisions, rejection-after-approval, unsolicited enrollment). Nothing material for correct invocation is missing.

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, but the description adds meaning by tying each enum value to a downstream consequence (approved enrolls and emails a link; rejected records and emails the note) and explicitly notes decisionNote appears in the rejection email only. That linkage is richer than the per-field schema text.

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 names a specific verb pair (approve/reject) and a precise resource (one course application from application_list), and it explicitly delineates itself from enrollment_revoke and enrollment_create. An agent can distinguish this from every sibling 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?

It gives explicit routing: use enrollment_revoke to remove an existing enrollment, and enrollment_create to enroll someone who never applied. It also states the idempotency behavior (repeating a decision does nothing; rejecting an already-approved application does not unenroll), which is exactly the when/when-not guidance an agent needs.

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