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

Annotations already declare the safe read-only, idempotent, non-destructive profile, so the bar is lower. The description adds real value beyond them: ordering (newest first), the returned dimensions (time, outcome, cost), and the status vocabulary (running, done, failed, cancelled).

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 lean sentences, newest-first ordering and the list-vs-single distinction front-loaded, and no filler whatsoever.

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 read-only list tool whose annotations carry the safety profile and whose parameters are fully described in the schema, the description tells the agent what it will get back. No output schema means return shape falls to the description, which it handles adequately via the outcome/status fields.

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 `run_id` and `limit` semantics are already documented in the schema. The description's contribution — that `run_id` yields a single run's current state and that status resolves to four values — is modest, so the baseline 3 applies.

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 the resource (a workbook's runs) and the exact content returned (when each ran, how it ended, cost), plus the single-run mode. Combined with the title it is unmistakably a listing tool, distinguishable from stop_run. It lacks an explicit verb in the description body, relying on the title to anchor intent.

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 implies two modes — omit `run_id` to list, supply it to get one run's status — but never states when to prefer this over siblings like get_trace or stop_run. Usage is inferable rather than explicit, fitting the 'implied usage' tier.

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