cli

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

With no annotations, the description carries the full burden, yet it only discloses that execution happens asynchronously as a background job. It says nothing about whether arbitrary commands can mutate or delete data, what permissions or environment are used, how failures surface, or that results must be retrieved via job_status/results.

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 'Advanced' qualifier and the verb front-loaded before the example. The trailing pointer to CLAUDE.md is a cheap external reference an agent cannot read at call time, but it costs little space.

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 catch-all command executor with no annotations, no output schema and an undocumented single parameter, the description is thin: it omits the return value (job handle), how to poll progress, timeout/rate-limit behavior, and any safety constraints on what commands are permitted.

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 compensate, and it partly does: the example shows args is an ordered argv list where element 0 is the subcommand and the rest are flags/values. It still gives no escaping, quoting, or shell-vs-direct-execution semantics.

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 any MarketMirror CLI command as a background job, with a concrete example argv array. It is clearly distinguishable as a generic escape hatch rather than a targeted operation, though it never names which siblings it supersedes.

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 'Advanced:' prefix implies this is a fallback when no dedicated tool fits, but that is inference, not guidance. There is no statement of when to prefer run_test, backtest, survey-workflow tools, or similar over raw CLI invocation, and no prerequisites or warnings about misuse.

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