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

Goes well beyond the annotations: it discloses that an account is still created even if the user declines, that prerequisites are enforced unless skipPrerequisiteCheck:true, the exact default email behavior (nothing sent unless sendInvite:true), that magic links are single-use/24h and minting cancels earlier links, the duplicate-enrollment side effect (no new record, created:false, but status label reset to "completed"), and the enrollment.created webhook. This is unusually rich side-effect disclosure for a destructive write 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?

Front-loaded with the core action and zero filler sentences, but it is one dense run-on paragraph where semicolon-joined clauses blend usage guidance, side effects, and return values. It would read better split into use-when / behavior / returns groupings, though nothing is wasted.

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?

With no output schema, the description compensates by enumerating the return shape ({enrollment, user, magicLinkUrl, created, emailSent, externalReference}) and explaining key values like created:false and emailSent. Combined with the side-effect coverage, an agent has everything needed to call this correctly.

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 cross-parameter behavior not in the schema: sendInvite overrides issueMagicLink, the magic link is what you use for your own welcome email, and no payment is recorded so checkout still shows. These interactions meaningfully extend the per-field descriptions.

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 first clause states a specific verb+resource (enroll one learner in a course by email) and immediately scopes it against siblings: enrollment_bulk_create for many learners, application_review for approvals. An agent can distinguish this from enrollment_update and enrollment_bulk_create without opening any 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?

Explicit alternatives are named with the condition that selects each: bulk create for many learners, application_review to approve an applicant, enrollment_update to change an existing enrollment. It also states what is NOT validated (price, application requirement, enrollment dates) and where to get course ids (course_list).

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