compute.fetch_results

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

Annotations only declare readOnlyHint=false, so the description carries most of the load and does so well: it discloses that data is written to a local directory, that a confirm flag is required as a write gate, and that integrity is checked via SHA-256. It omits what happens on a re-fetch or when files already exist at dest, which is the main remaining gap.

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 short sentences with no filler; the core action is front-loaded and the write/confirm caveat follows immediately. Every clause adds information an agent needs.

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 four-parameter write operation with no output schema, the description should say what is copied (all artifacts? logs?), whether the destination must be empty, what force does, and what is returned on success. The confirm gate and verification step are covered, but those remaining gaps keep it at merely adequate.

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 define all four parameters and it only covers two implicitly: dest ('local directory') and confirm ('needs confirm=true'). The 'force' flag and 'run_id' receive no explanation at all, leaving an agent to guess what forcing does or whether it overwrites existing files.

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 ('Copy a run's artifacts to the control machine') and even the transfer mechanism (tar + scp, SHA-256 verified), which is far more concrete than the tool name alone. It does not distinguish itself from the similarly-named sibling compute_collect_results, so it falls short of a 5.

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?

Usage is only implied: fetching artifacts presupposes a completed run, and the description states the confirm=true prerequisite. It never says when to choose this over compute_collect_results or compute_get_logs, nor does it state any preconditions such as run status.

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