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

With no annotations, the description carries the full disclosure burden. It usefully reveals that traces are *stored* and only available for terminal runs, implying non-terminal runs yield nothing — genuine behavioral context. It says nothing about permissions, whether traces expire, or that include_io materially changes payload size, which is a real gap for an unannotated read tool.

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 sentence, front-loaded with the verb and resource, with the terminal-run constraint appended. Nothing redundant or padded.

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 both parameters are fully covered by the schema. The remaining gap is routing guidance against the many agent_run_* siblings and clarity on which terminal states have persisted traces.

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 100%, and the schema already fully documents run_id and include_io including default and size limits. The description adds no parameter meaning beyond that, so the baseline 3 is appropriate.

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?

States a specific verb (Return) and a specific resource (the stored model/tool/error trace tree), which is clearly distinct from sibling readers like agent_run_status or agent_run_list. It does not explicitly name a sibling alternative, but the resource is specific enough that an agent can tell 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?

"for a terminal run" gives an implied precondition — the run must be finished — which is meaningful selection guidance. However, it never states what to use for a live/in-progress run (agent_run_status) or whether cancelled/failed runs qualify as terminal, so alternatives are left to inference.

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