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

Annotations already cover readOnlyHint and openWorldHint, so the bar is lower; "Free, offline" still adds real value by confirming no network egress or quota/cost concerns for pre-execution screening. The list of flagged patterns further discloses detection behavior, though it never says whether results arrive as a verdict, a findings list, or a risk score.

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?

One dense sentence with the key qualifier ("Free, offline") and the timing imperative ("Call BEFORE") both front-loaded. No filler, and each clause contributes a distinct detection category.

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 one-parameter read-only checker with no output schema, the description covers purpose, timing, and detection scope well. The remaining gap is the return shape — an agent cannot tell whether it gets a boolean verdict, a severity level, or per-pattern findings, which matters for deciding whether to run the command afterward.

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 100% and the single parameter is already described as "command or text block". The description adds modest context by implying pasted multi-line snippets from READMEs/issues/chat are acceptable input, but nothing about size limits, escaping, or how to pass multi-command blocks. Baseline 3 applies.

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 states a concrete action (inspect a shell/PowerShell command before execution) and enumerates exactly what it detects — download-and-execute, encoded PowerShell, LOLBins, AV disabling, malware domains, pipe-to-shell. The resource (a single command) is implicitly distinct from check_repo's repository scope, but that contrast is never made explicit.

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?

"Call BEFORE running a shell/PowerShell command copied from a README, issue, website or chat" gives a clear trigger condition and a source-of-input qualifier. It stops short of stating when not to bother (e.g., self-authored commands) or pointing at check_repo as the alternative for repo-wide analysis.

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