get_run

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

With no annotations, the description carries the full burden, but it does disclose one genuinely useful behavior: oversized records are returned as an explicit summary plus an artifact handle rather than inline payloads. That is real context an agent would otherwise not know. It still omits the safety profile (read-only, non-destructive) and error behavior for an invalid run_id, so it is only partially transparent.

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?

One compact sentence with the primary action front-loaded and the noteworthy behavior in the trailing clause. Nothing is wasted, though the extreme brevity pushes some load onto the caller rather than the text.

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?

An output schema exists, so return values need not be described, and the one behavioral surprise (summary plus artifact handle) is called out. For a single-parameter read tool this is nearly sufficient; only the provenance of run_id and the read-only guarantee are absent.

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?

Only one parameter exists and its schema description coverage is 0%, so the description would ideally explain what run_id refers to and where to obtain it. It adds nothing on that point. With just a single, self-evidently named required parameter, this is a modest rather than severe gap.

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 gives a verb ("Read") and a scope ("status/results"), and the tool name supplies the resource (a run), so the basic purpose is inferable. However it never says the word "run" or otherwise anchors what object is read, and it does nothing to distinguish this from siblings such as compare_runs or the various get_* readers. Purpose is implied rather than stated.

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?

There is no indication of when to call this versus list_runs, compare_runs, or the other get_* tools, and no prerequisites (e.g. needing a run_id from list_runs) are mentioned. The only guidance-like content is the note about large records, which is about output shape, not tool selection.

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