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

With annotations already declaring readOnlyHint=false, idempotentHint=true and destructiveHint=false, the description adds genuinely non-redundant context: it is asynchronous (queues a hosted job, result via get_job) and, critically, it is gated on real user approval with an explicit warning not to fabricate approval fields. That approval/auth requirement and the async model are not derivable from the 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?

Three short sentences, front-loaded with the core action and constraint, then the async behavior, then the approval gate. No filler sentences and 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 10-parameter, nested-object mutation with no output schema, the description omits explanations of the concurrency guard (expectedRevision), the retry contract (idempotencyKey/requestId) and the renames mapping. The approval and get_job notes are covered, but the parameter surface an agent must populate is largely unaddressed.

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 only 30% (uploadId, requestId, workspaceToken documented), leaving 7 of 10 parameters undescribed in both schema and description. The description mentions 'approval fields' only, adding nothing about expectedRevision (optimistic concurrency), idempotencyKey, renames, waveId or label, so it fails to compensate for the low coverage.

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 and resource ('Import a replacement wave') and adds a meaningful constraint ('without overwriting prior source data') that distinguishes it conceptually from import_dataset. It stops short of naming the sibling it competes with, so an agent must infer that distinction.

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?

Gives useful procedural guidance ('Queues a hosted job; use get_job to retrieve its result') and a precondition ('obtain actual user approval before calling'). However it never states when to choose replace_dataset over import_dataset, or what distinguishes a 'replacement wave' from a new import, which is the central routing decision here.

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