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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false), and the description adds substantive facts beyond them: 10 MiB / 50,000-record ceilings, UTF-8 CSV/JSONL only, and 24-hour retention. It still omits whether re-uploading replaces or accumulates data and whether the returned handle is needed downstream, but the added operational constraints are genuinely useful.

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 immediately followed by hard limits and the retention window. Every clause carries information; only the missing mention of the result handle keeps it from being optimal.

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 write tool with no output schema and zero schema coverage, the description covers input constraints and retention but not the outcome an agent needs to chain into the import workflow. The ephemeral 24-hour window implies a follow-up call, yet the description never names the handle or the next step.

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 carry the load. It effectively defines the content parameter (UTF-8 CSV or JSONL, capped size/records), but never maps the 'format' parameter to its allowed values or says which value pairs with which payload shape, leaving the agent to infer csv/jsonl.

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 gives a concrete verb and payload: it uploads inline content in UTF-8 CSV or JSONL, with size and record caps, and explicitly excludes URL/path sources. That distinguishes its input mode from siblings like preview_supplier_feed or start_supplier_import, though it never states what an upload produces (a feed handle/ID) or how it relates to those downstream tools.

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?

There is no when-to-use guidance relative to the eleven siblings. 'No URL or local file paths' is an input restriction rather than a routing rule, and nothing says whether upload_supplier_feed must precede start_supplier_import or preview_supplier_feed, or when to choose create_supplier_feed_profile instead.

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