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

Annotations cover the safety profile (readOnly=false, idempotent=false, destructive=false), and the description adds real operational context beyond them: single-use handle, 1-hour default expiry, a 15-minute unauthenticated POST window, and automatic legacy-column mapping. These are the traits that change how an agent sequences the call.

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-loaded with purpose before mechanism, and every sentence carries load: input routes, column mapping, redirect rule, handle lifecycle. No filler or restatement of the tool title.

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 staging tool with no required params and an output schema, the description supplies everything an agent needs: the four input paths, the target build (direct_build), the redirect case, and handle expiry. Return values are covered by the output schema and reinforced by the upload_handle mention.

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 largely does: csv_text behavior (newlines preserved), upload_handle for chunked appends, and the expiry semantics behind ttl_seconds. The assignments array is only implicitly referenced as 'assignment chunks', leaving the fourth input route slightly less precise than the others.

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 (stages) and resource (part-to-territory assignment rows), with a concrete example and the return value (upload_handle). It also explicitly distinguishes itself from the sibling request_account_upload, so an agent can separate the two without opening a schema.

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?

Says this feeds direct_build as a consumer, enumerates the four accepted input routes, and gives an explicit when-not with the alternative ('A file of locations rather than assignments is redirected to request_account_upload'). Nothing about selection 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.