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

Annotations already establish readOnly, idempotent and non-destructive, so the lower bar applies; the description still adds genuinely useful behavior: the call blocks for up to 20 seconds waiting for completion, and 'Reading does not start the work again' reassures the agent that polling is safe. It stops short of describing what a still-running response looks like or how cursor paging composes with repeated polling.

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?

Four sentences, front-loaded with the purpose and the list of job kinds that anchors it, then the wait semantic, then the failures-paging note. The failures sentence duplicates schema wording somewhat, but nothing is filler.

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 6-parameter polling tool with no output schema, the description covers what is returned at a high level ('state, progress and result') and the failure-paging mode. It leaves the response shape and cursor-based pagination unexplained, which an agent needs when a job exceeds the wait window.

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 67% and the schema already documents detail, include and mode in comparable terms, so the description's 'include: failures pages the failed rows' is largely reinforcement with concrete job-type examples. The description never mentions cursor, which is undocumented in the schema too, and 'waits up to 20 seconds' describes the maximum rather than the 15-second default. Baseline 3 fits a schema carrying most of the parameter weight.

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 and resource ('Reads the state, progress and result of a job') and enumerates the job origins an agent will encounter: basket search plans, inventory import/export/bulk edit, repricing runs, shipment batches. That enumeration maps directly onto creating siblings such as apply_basket_plan, start_inventory_import, apply_reprice and mark_orders_shipped, so the tool is clearly distinguishable from them.

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 description makes clear this is a follow-up tool used only after 'another tool started' the work, which is exactly the when-to-use condition. It does not name an alternative (there is no real sibling that also polls jobs) and does not state what to do if the job is still running after the wait window, which keeps it short of a 5.

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