krl_lint_snippet

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

With no annotations, the description carries the full burden; it does disclose that the analysis is static/offline and lists the checks performed, which implies a non-mutating read. It does not say whether findings carry severity or line numbers, what happens on unparsable input, or confirm that no code is executed or modified.

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 sentences, no filler, with the tool's nature front-loaded and the check list used efficiently to convey capability. Every clause 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?

For a one-input linting tool with no output schema and no annotations, the definition should at least indicate the shape of the result (list of findings with locations/severities). It covers what the tool looks for but not what the agent gets back or how to interpret a clean run.

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?

There is a single required parameter with 100% schema description coverage, so the schema already defines 'code' adequately. The description adds no constraints or format details (encoding, size limits, full module vs fragment) beyond what the schema states, so 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?

States a specific verb and resource ('static code analysis for KRL code snippets') and then enumerates the exact defect classes it detects (uninitialized $TOOL/$BASE, loops without EXIT, division by zero, unbalanced folds, I/O overflows, non-ASCII). The 'snippet' scope distinguishes it from the workspace/file-level siblings such as krl_workspace_diagnostics and krl_deep_safety_audit.

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 words 'Fast offline' imply this is the lightweight, no-workspace-needed check, which hints at when to prefer it. But no sibling is named and there is no explicit when-not guidance (e.g. use krl_deep_safety_audit for a full audit, krl_workspace_diagnostics for whole-project scanning), leaving routing to inference.

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