Shell

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

No annotations are provided, so the description carries the full burden. It does disclose the return shape and the enablement flag, but for an arbitrary-code-execution tool it omits the critical traits: that it can mutate or delete anything on the host, run network operations, and has no stated sandboxing or permission model. The 'Disabled by default' note is the only safety signal, which is far short of what this tool requires.

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 clauses with zero padding; the purpose is front-loaded and the operational constraint follows. Every word earns its place.

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 the description need not explain return values (though it helpfully does). What is missing for a high-risk, zero-annotation, three-parameter tool is any warning about destructiveness or execution scope, and any semantics for cwd/timeout_s. Adequate at minimum but with clear gaps given the tool's risk profile.

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% and the description mentions none of the three parameters. 'cmd' is obvious from context, and 'cwd'/'timeout_s' are fairly self-describing names, but there is no statement of default working directory, units or default for the timeout, or what happens when the timeout fires. The description does not compensate for the coverage 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?

States a specific verb and resource ('Execute a shell command') that is unmistakably distinct from every sibling, which are all file/search/memory operations. An agent can immediately tell this is the arbitrary-command tool and not a filesystem helper.

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 description gives an availability prerequisite ('Disabled by default; set MCP_BASH_ALLOW=1 to enable'), which is genuinely useful for knowing whether the tool will work at all. However it never says when to prefer Shell over siblings like ReadFile, WriteFile, or SearchText, nor any when-not-to-use condition.

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