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

Annotations only declare readOnlyHint and openWorldHint=false; the description adds far more: blocking wait behavior, the fact that the tool is free, list-run expiration, the exact termination signal (completed_at + progress 100), and a prompt-injection warning that row values are customer data, not instructions.

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 return contents before the usage detail, and every sentence earns its place. It is dense and reads as one long run-on, which slightly hurts scanability, but there is no 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?

With no output schema, the description carries the full burden of explaining return fields (completed_at, progress, verdict_line, filled/empty/failed counts, samples) and does so. Combined with the polling and hand-off guidance, an agent has everything needed to call this correctly.

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 100%, so both parameters are already documented; the description reinforces wait_seconds semantics (up to 50) and introduces polling behavior via next_check_seconds, which meaningfully explains how to use the wait/timeout pair together. It adds real meaning over the schema but nothing hidden about run_id.

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?

Names a specific verb+resource ('Status of a run you started') and enumerates exactly what it returns: row counts, progress, cost, common error codes, and list expiry. It distinguishes itself from get_run_rows/export_list by telling the agent those are for finished list-run results.

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?

Gives explicit polling instructions: pass wait_seconds (up to 50) to block, otherwise re-call after next_check_seconds. It also routes the agent away from reading every row ('report the verdict') and toward get_rows/export_list for finished list runs, and states a sheet run writes into the sheet instead.

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