Import orders from CSV text (1 MiB max); the same sourceId is idempotent

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description goes well beyond that by disclosing the 1 MiB payload cap, the confirm gate, the absence of a server-side dry run, and sourceId-based idempotency. It does not cover auth/permission requirements or what happens on partial/row-level CSV failures, which keeps it short of 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?

Two tight sentences, zero filler, with the write-gating warning and size limit front-loaded before the endpoint detail. Every clause carries actionable information.

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 nested-body write tool with no output schema, it covers the safety profile, size limit, idempotency, and confirm preview behavior — enough to call it correctly. Row-level error handling and response contents are the remaining gaps, though the schema documents the preview-on-no-confirm behavior.

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 67%, and the description adds real meaning for the two most consequential parameters: sourceId drives idempotency, and confirm gates actual execution versus a preview. clientId and currency are left entirely to the schema, so it compensates only partially for the coverage gap.

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 uses a specific verb+resource ('Import orders from CSV text') and adds a concrete constraint (1 MiB max) plus the underlying endpoint (POST /v1/revenue/csv). It is clearly distinguishable from write-adjacent siblings such as revenue_backfill or tracking_ingest, though it never names those alternatives explicitly.

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?

It gives clear operational context: the call is a WRITE that only executes with confirm: true, there is no server-side dry run, and reusing sourceId is idempotent. What it lacks is explicit routing guidance — when to prefer this over revenue_backfill or conversions_send is left to inference.

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