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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real context beyond them: page caps of 500 records / 64 KiB, a seven-day availability window, ownership scoping, and the fact that oversized records need an authenticated download of download_path. That is meaningful operational disclosure rather than restatement.

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 operation and paging limits, with no filler. Density of constraints makes it slightly hard to parse on first read but every clause carries information.

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 output schema, the description does the work of describing the return shape (JSONL records, next_offset for continuation, download_path for oversized records) and the retention limit. It is close to complete for a read tool; missing only what happens when the job is not passed or when the seven-day window has expired.

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 for three bare parameters. It explains the page-size cap (500/64 KiB) for limit and the continuation mechanic for offset, but it refers to 'next_offset' while the actual parameter is named 'offset', a naming mismatch that could confuse. job_id semantics ('owned passed job') are only hinted at.

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 names a specific verb and resource ('Read validated JSONL ... for an owned passed job') and scopes it to paged output, which distinguishes it from the report/preview siblings. It is dense with jargon ('validated', 'passed job') but an agent can still tell roughly what it retrieves.

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?

It states the preconditions for use (job must be owned and passed, within seven days) and how to continue ('Follow next_offset'), which implies the usage context. But it never tells the agent when to choose this over get_supplier_import or get_supplier_import_report, which is the critical routing decision among these siblings.

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