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

Goes beyond the annotations (destructiveHint=false, idempotentHint=false) by disclosing the outcome of non-idempotency: a retry after timeout can create duplicate documents, so the agent must verify Drive first. It also states the return value (document URL) and the rejection behavior for unsupported artifact types.

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?

Two front-loaded sentences plus the endpoint path; every clause carries information (destination mapping, refusal rule, return value, retry hazard) with no 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 3-param, no-output-schema export tool, the description covers selection between destinations, artifact eligibility, success output, and failure/retry handling. Nothing an agent needs to invoke it correctly is missing.

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 meaning the schema doesn't: the artifact parameter must reference a completed report or data table, tying the artifact's type to the required destination value. Title and id-format semantics are left entirely 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?

States a specific verb ('Export') and resource ('artifact') and precisely maps each destination enum value to the artifact type it accepts, making it distinguishable from siblings like notebook_generate_artifact or notebook_copy_artifacts. The refusal clause ('other types are refused') sharpens scope further.

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?

Tells the agent which destination to pick for which content type (docs for reports, sheets for tables) and gives a concrete operational rule for timeouts. It stops short of naming an alternative sibling tool for cases where export isn't the right move.

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