run_command

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

Annotations already flag destructiveHint=true, but the description adds genuinely new behavioral context: commands are drawn from an allow-list, shell metacharacters (| ; > *) are not interpreted, path arguments are sandboxed to allowed folders, and mutations gate on confirm=true. It stops short of saying what happens when confirm is omitted on a mutating command (error vs silent skip) or how the allow-list is scoped.

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 compact sentences with the execution model front-loaded and the confirm rule last where it matters most for a destructive tool. The parenthetical example list is efficient; only minor whitespace/formatting noise detracts.

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 no explanation, and the safety story is well covered. However, for a destructive, 4-parameter tool with zero schema descriptions, the missing `timeout` semantics and `cwd` meaning leave gaps an agent would have to guess at.

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 carry parameter meaning. It explains `command` (allow-listed only) and `confirm` (required for cp/mv/git pull style operations), but says nothing about `cwd` as a parameter or about `timeout`, leaving two of four parameters undocumented anywhere.

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 and resource ("Run an allow-listed command") plus the execution model (no shell interpretation). This separates it from read-only siblings like read_file and from specialized executors like asterisk_cli or db_query, though no sibling is named 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?

Gives concrete preconditions for invocation: path arguments must be inside allowed folders and mutating commands (cp, mv, git pull) require confirm=true. These are constraints rather than when-to-use-vs-alternative guidance, so an agent still has to infer that arbitrary shell scripting is impossible and which tool to pick for non-allow-listed work.

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