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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the safety profile is partly covered. The description adds materially beyond that: the operation is paid ($49 Stripe / $0.75 x402 USDC), there is a free preview escape hatch, output is verified via 'stem-withheld blind-QA item verification,' and delivery is via the archive email. It still omits failure behavior (what happens on a bad payment_token) and turnaround/async expectations.

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?

The core purpose is front-loaded in the first clause, and the parentheticals each carry distinct facts (price, preview alternative). It is a single long run-on sentence with dense jargon ('stem-withheld blind-QA item verification'), which costs some readability, but no sentence is filler.

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 paid, non-idempotent compilation tool with no output schema and six fully documented parameters, the description covers what is produced, what it costs, and how to get a free sample. Remaining gaps are operational rather than definitional: no statement of delivery timing, failure modes, or whether repeated calls with the same input re-charge.

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. The description goes past the schema by tying the price to the two payment rails mentioned in payment_token ('$49 Stripe / $0.75 x402 USDC') and by restating preview_mode as the free path, giving the agent a reason to choose that flag rather than a bare default. It does not clarify how payment_token is validated or what preview_mode omits from the paid output.

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 ('Compiles') and a concrete resource pair ('raw Markdown/text SOPs, runbooks, or training docs') mapped to a specific artifact ('LMS-ready SCORM 1.2 + IMS QTI 3.0 XML mastery packages'). It does not distinguish itself from any sibling, but the sibling names listed (audit_workflow_guardrails_50v, build_rea_har_agent_sandbox, etc.) are in unrelated domains, so the purpose still lands unambiguously.

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?

Usage is implied by the input-to-output framing rather than stated: an agent can infer 'use this when you have an SOP needing SCORM/QTI packaging.' The one explicit routing hint is 'set preview_mode=true for a free Knowledge Component + QTI 3.0 XML item preview,' which tells the agent how to sample before paying. There is no stated when-not, no prerequisites (e.g., payment_token required for production), and no named alternatives.

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