tokportal_create_bundle

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

Annotations only provide readOnlyHint=false, idempotentHint=false, destructiveHint=false, and title, leaving significant behavioral details undisclosed. The description compensates thoroughly: it reveals credit debit timing (immediately vs. at publish), the cutoff for new-customer benefits (immutable production instant from getCreditCosts), the idempotency model (external_ref vs. Idempotency-Key), and the auto-cancellation policy for unconfigured warming terms. No contradictions with annotations.

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 description is information-dense but not concise. It packs 8+ distinct behavioral rules into a single block of 8 sentences, lacking visual structure (no bullet points or section breaks). The first sentence is immediate and clear, but the density may overwhelm an agent. A more structured approach (e.g., subsections for 'Payment', 'Warming Terms', 'Idempotency') would improve scannability.

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?

Given the tool's high complexity (2 params, nested object with 16 sub-fields, no output schema, and 66 siblings), the description covers the most critical behavioral aspects: atomicity, credit timing, warming term configuration, and idempotency. It lacks guidance on response format (what fields to expect on success/error), and the schema already handles parameter validation. A small gap exists in not describing the 'edits_quantity' or 'videos_quantity' semantics, though those are somewhat self-explanatory.

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 100%, so baseline is 3. The description adds significant value beyond the schema: it explains the relationship between advanced_warming_terms and advanced_warming_terms_count (pass one or the other), the auto-cancellation behavior for count-only purchases, and the distinction between external_ref and Idempotency-Key. However, the description doesn't explicitly connect each schema parameter to the broader workflow—some details (like the country requirement exception for videos_only) are left to the schema.

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 clearly states the verb ('Create a bundle'), the resource ('bundle'), and specifies three bundle types (account-only, account-and-videos, videos-only) with the critical detail of atomic creation checkout. It distinguishes this from sibling tools by emphasizing the atomic payment and creation aspect, which no other sibling tool (like tokportal_create_bundles_bulk or tokportal_update_bundle) covers.

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 provides extensive when-to-use guidance: it explains prerequisites (getCreditCosts for credit cost), the credit debit timing (immediately on POST, not at publish), and implicit alternatives (e.g., configuring warming terms later via PUT /bundles/{id}/warming-terms). It also defines conditions for auto-cancellation and refunds (14 days for unconfigured count-only purchases), helping the agent decide when this tool is appropriate.

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