tokportal_create_account_edit_request

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

Annotations are minimal (non-read-only, not destructive, not idempotent), so the description carries the full behavioral burden. It credibly discloses that the operation debits 8 credits, is atomic (assignment, debit, task creation are tied together), creates a task in a manager's calendar, and handles completed bundles without delivery-age limit. It also states cancelled orders are never restored, which is critical behavioral info not captured by annotations. No contradictions.

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 dense but not verbose—six sentences covering purpose, prerequisites, process, and atomicity. Every sentence adds specific value (e.g., 'debits 8 credits', 'completed bundles remain eligible'), and the critical atomicity guarantee is front-loaded after explaining prerequisites. No extraneous content.

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 has three parameters (two required), no output schema, and moderate complexity (nested object, credit cost, manager routing), the description covers all essential aspects: prerequisites, credit cost, manager fallback logic, atomicity, and bundle eligibility rules. No return value is described, but the description implies the task appears in a calendar, so the outcome is clear. This is complete for the tool's complexity and schema richness.

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% with detailed parameter descriptions (e.g., id is a UUID saved account ID, body includes fields like requested_biography with platform-specific length notes). The description adds high-level context about the body being profile changes and id referencing delivered accounts, but the schema already does most of the work. One could argue the description doesn't tie the parameters to the atomic flow, but the schema is sufficiently rich.

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 tool requests profile edits for a delivered account, specifying the action (request profile edits), the resource (delivered account), and the scope (profile changes). It also distinguishes itself from siblings like tokportal_get_account_edit_request (which retrieves requests) and tokportal_configure_bundle_account (which configures account properties), making the purpose unmistakable.

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 explicit prerequisites: active TokPortal Coverage and a routable active account manager. It details the manager selection order (current active manager, still-active relationship, then eligible non-cancelled order history), which guides when the tool can be used. It also clarifies atomicity and that unavailable managers do not cost credits, implying safe retry conditions without explicitly stating alternatives. This is comprehensive guidance.

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