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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. "Persisted" usefully signals durable stored state rather than live execution, and "row receipts" signals per-row granularity, but the "cannot start or approve" clause largely restates what readOnlyHint already conveys rather than adding new behavioral context.

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?

Two short sentences, no filler, with the resource scope front-loaded and the boundary condition second. Every clause carries load.

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?

With no parameters, no output schema and all annotations present, the description needs to say what comes back, and it does: import plans, progress and row receipts. Minor gaps remain (no indication of ordering, volume or whether all historical jobs are returned), but nothing essential to correct invocation is missing.

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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly implies the query scope is implicit (the current connection) rather than parameterized.

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?

Specific verb ("Inspect") plus a precisely scoped resource ("this connection's persisted import plans, progress and row receipts"), which is more informative than the title's generic restatement. It separates itself from status tools like get_bulk_upload_status by naming the concrete artifacts returned, though it never names a sibling alternative outright.

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 negative constraint "Cannot start or approve them" clearly delimits when this tool is the wrong choice, which is the main confusion risk for an 'import jobs' endpoint. It lacks an explicit positive trigger (e.g. 'use when you need to audit a failed import run') and does not route to the sibling that would start or approve jobs.

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