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

With no annotations provided, the description carries the full burden. It does well on side effects ("Creates nothing, no credits") and enumerates what is returned, but says nothing about authentication/permission requirements, whether the preview is retained server-side for the subsequent upload, or how the suggested mapping is derived (and thus when to override it).

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?

Front-loads the purpose and keeps the pipeline note at the end; every clause carries information. The return-value enumeration is a bit list-like but earns its place given there is no output schema.

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?

No annotations and no output schema, so the description must supply both safety and return shape — and it does. The remaining gap is whether the preview must be immediately followed by the upload (statefulness/expiry) and any permission prerequisites, which an agent planning a multi-step upload would want.

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%, including size caps and the either/or relationship between file_url and content_base64, so the schema already documents all three parameters. The description only adds accepted formats and that column_mapping (a parameter of the *next* tool) can be corrected, so baseline 3 applies.

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 concrete verb (send a file, get detected headers/mapping) and the exact resource (contacts file for a custom audience upload). It also labels itself "Step 1 of an upload", which cleanly separates it from the sibling upload_custom_audience that performs step 2.

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?

Explicitly states the sequencing ("Then call `upload_custom_audience` (optionally with a corrected column_mapping)"), which tells the agent both the alternative and the condition for using it. The "Creates nothing, no credits" note further clarifies this is a safe pre-flight step rather than a substitute for the upload.

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