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

Annotations only disclose readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the description carries most of the burden and does well: documents stay pending until admin acceptance, screening is not verification, never pay or sign, idempotency/retry and confirmation-boundary rules. The generic canonicality/idempotency/confirmation boilerplate is somewhat mechanical, keeping this from a 5.

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 instruction is front-loaded, but the description runs long and is padded with boilerplate canon (canonicality, idempotency, confirmation boundary) that reads as generic appended text rather than earning its place. The logo/email-domain follow-up steps are crammed in, making it harder to scan for the primary action.

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 complex tool with a nested schema, no output schema, and no rich annotations, the description covers prerequisites, pending-state behavior, idempotency, confirmation boundaries, and downstream follow-ups. It is broadly complete, with only the parameter-level detail (companyId, quantity, enum meanings) left thin.

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 0%, so the description must compensate. It conveys the meaning of the choices array (existing documents vs services Corply should perform, mapping loosely to have/corply/not_applicable) and implies itemKey semantics via the asked questions, but never explains companyId, the enum values explicitly, or the quantity field.

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 opening sentence states a specific verb (save) and resource (the founder's multiple-choice answers for company documents/missing services), which is concrete and actionable. It does not, however, differentiate itself from close siblings like confirm_import_intake, create_import_intake, or answer flows, so the agent must infer placement from the fleeter enum names. Clear but not fully disambiguated.

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?

Provides concrete operating guidance: ask one question at a time, never assume documents, offer the HTTPS PDF import, and the prerequisite of authenticated active company access. It never names a sibling alternative or says when NOT to use it (e.g., vs the confirm/get import tools), so it stops short of full routing guidance.

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