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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description discloses cost behavior that annotations cannot: which actions are free, that create/run queue billable rows, that failed/not-found/duplicate rows are never billed, that the estimate is the ceiling, and that runs are serialized per marketplace. It also flags the API-key requirement. It stops short of saying whether action=delete also discards stored results — a real gap for a destructive tool.

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 the core purpose, and each semicolon-delimited clause carries unique information (action semantics, kinds, billing, cost). It is dense to the point of being a wall of text for a 31-parameter tool, but almost nothing is redundant.

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 31-parameter multi-action tool with no output schema, the description covers action selection, kinds, cost, scheduling semantics, and pagination well enough to call correctly. Remaining gaps are the three undocumented numeric tuning parameters and any indication of the shape of status/results payloads beyond the mentions of rows/credits/queue position and download URLs.

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 90%, so the baseline is 3; the description still adds value by defining each action's semantics (estimate vs create vs run vs status vs results) and by explaining that endpoint kinds take the endpoint's own query parameters in params. It also pins concrete meaning onto source=tracked with include [history_only] and its 0.05/row cost. It does not cover max_age_days, history_points, or history_sellers, which carry no schema descriptions 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 opening sentence names a specific verb and resource ('run any Logimu endpoint over a whole list in one job') and immediately scopes it as the batch counterpart to REST /v1/batches. Every action is enumerated with its own one-clause meaning, so an agent can distinguish this from single-item siblings like product or search 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?

The 'USE WHEN' clause gives an explicit trigger threshold ('more than a handful of ASINs, barcodes, search terms, seller ids, brands or seeds'), plus scheduled refresh and CSV output as alternate triggers, which implicitly routes single-item requests to the non-batch siblings. Kind selection is also spelled out per data type, leaving little to inference.

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