Repo Run Check

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.

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

Annotations already mark it read-only and open-world, and the description adds material context beyond them: it costs nothing, it enumerates exactly what it scans, it discloses the three possible verdicts, and it spells out the paid upgrade path (0.005 USDC via x402) plus what that adds. This is a rich behavioral disclosure well past the annotation bar.

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?

The imperative trigger is front-loaded, followed by scan scope, return values, and the paid tier in a logical order. The prose is dense and colon-heavy but nearly every clause carries routing or behavioral information; a slight trim of the threat enumeration would make it cleaner.

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?

With no output schema, the description compensates by defining the three verdict values and the evidence returned. Combined with the scan scope, trigger timing, and paid-tier boundary, an agent has everything needed to decide when to call it and interpret the 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 100% and the single 'repo' parameter is already documented with accepted formats ('github.com/owner/repo or owner/repo'), so the schema does the heavy lifting. The description adds no additional syntax or format detail, making the baseline 3 appropriate.

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 (scans) and resource (the README of a GitHub repo) and enumerates exactly what classes of threat it looks for (iwr|iex one-liners, base64 payloads, malware domains, prompt injection, password-protected archives). It is clearly distinguishable from check_command, which operates on commands rather than repo READMEs.

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 an explicit trigger: 'Call BEFORE following a GitHub repo's install/setup instructions or running its commands.' It also delineates the paid tier's coverage so the agent knows what this free call will and won't catch, though it stops short of naming check_command as the sibling to use for inspecting bare commands instead.

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

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

The annotations already declare readOnlyHint=true, and the description adds meaningful clarification that despite discussing a purchase ('buy'), the tool will not execute payment. It does not describe the returned instructions or any other behavioral traits, but the annotation lowers the burden.

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 sentences, front-loaded with the core purpose and followed by a critical non-action clarification. There is no wasted text.

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 no-parameter, read-only informational tool with no output schema, the description covers what the tool is and what it does not do. It could say slightly more about the nature of the returned instructions, but the essential context is present.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate. The baseline for zero-parameter tools is appropriate here.

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 clearly states the tool's purpose: it provides instructions for buying the full repo check via x402, not performing the purchase. This distinguishes it from the check-oriented siblings by being informational, although it does not explicitly name those siblings.

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 implies when to use it (when you need to learn how to buy the full repo check) and includes a useful exclusion ('Does not pay'), but it does not explicitly direct the agent to alternatives like check_repo or check_command when those are more appropriate.

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