Sa360.Conversion.Upload

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

With no annotations, the description carries the full burden, and it does disclose the most important behavior: the operation is guarded by a preview-plus-token confirmation gate, so an agent knows not to fire-and-forget. However, it omits permissions needed, token lifetime/single-use semantics, whether re-uploads are deduplicated or idempotent, and what the preview stage returns.

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?

One short sentence with the guarded behavior front-loaded and no wasted clauses. Its brevity is efficient, though it edges into under-specification given the payload complexity.

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 mutation tool with zero annotations, a 0%-documented schema, and an unconstrained conversions payload, the description is too thin. Output schema coverage reduces the need to describe returns, but the agent still lacks the payload shape and the instructions for obtaining and using the confirm token — the two things needed to call this correctly.

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, and it only partially does: "confirm token" loosely explains the `confirm` parameter. `customer_id` is unexplained and the `conversions` array — the core payload, declared as free-form objects with additionalProperties:true — is given no field shape, required keys, or formatting guidance at all.

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 states a specific verb and resource ("Upload SA360 conversions") and parenthetically discloses the guarded two-phase flow. The name and prefix already separate it from the sibling families, though it never explicitly distinguishes itself from the similarly named datamanager.conversions.upload.

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?

"Guarded: preview + confirm token" implies a two-step call pattern, but the mechanics are left to inference: it never says the first call must omit `confirm`, that the response yields the token, or when to prefer this over datamanager.conversions.upload. Usage is suggested, not stated.

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