atr_run

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

Annotations already flag this as open-world and destructive, and "run a shell command" is consistent with that. The description adds genuinely new behavioral context — that output is filtered so only failures are kept — but omits that arbitrary commands execute with side effects, that output may be lossy, and how the compression budget behaves.

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?

A single front-loaded sentence with no filler; the use-case examples and the output guarantee are both packed in, and nothing is redundant.

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 an open-world command executor with no output schema, the description does well to characterize the returned output. But with a destructive, side-effecting tool and an entirely undocumented `budget` parameter, an agent still lacks enough to call it confidently or predict the full result.

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 only 50%: `cwd` and `timeout` are documented in the schema, but `command` and especially `budget` are bare. The description never explains what `budget` controls, even though "compressed output" strongly implies it caps the returned size — the one place the description could have added real value.

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?

"Run a shell command" is a specific verb+resource, and the parenthetical (tests, build, lint) plus "compressed output: failures kept, noise cut" tells the agent exactly what it gets back. It is clearly distinct from every sibling (read/find/query/diff/stats tools), though it never says so explicitly.

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?

The examples (tests, build, lint) imply the intended context, but there is no explicit when-to-use vs. when-not, no mention of the sibling tools it might be confused with, and no guidance on when to prefer atr_read_file or atr_search_code over shelling out.

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