check_custom

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

With no annotations, the description carries the full burden of behavioral disclosure. It goes beyond a generic statement by disclosing the plugin loading mechanism, the skip behavior based on `applies_to.has_columns`, and that each finding includes the plugin name in `evidence.plugin`. This provides meaningful insight into how the tool operates. It does not mention side effects or performance, but for a check tool the disclosed behavior is substantive.

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 description is three sentences, front-loaded with the main action in the first sentence. Each sentence adds distinct value: action, loading context, and output behavior. There is no fluff or redundancy, and the structure is easy to scan.

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?

Given a single parameter, existence of an output schema, and the presence of many sibling check tools, the description is sufficiently complete. It explains the plugin source, the skipping logic, and the output format, which is enough for an agent to decide when to use it and what to expect. It could mention error handling or cost implications, but these are not critical for basic usage.

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 schema has 0% coverage and the description only references `source_id` as the target ('against `source_id`'). This adds minimal meaning beyond the parameter name itself. It does not explain what source_id represents, how to obtain it, or any constraints. For a single parameter with no schema description, the description should compensate, but it largely restates the parameter name.

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 a specific action: 'Run every loaded plugin (custom YAML+SQL check) against `source_id`.' It identifies the resource (plugins), the target (source_id), and the nature of the operation. It also differentiates from sibling check tools by specifying it is for custom plugins, not built-in checks.

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 clear context on when to use the tool: when you want to run all loaded custom plugins. It explains how plugins are sourced (plugins_builtin/ directory and --plugins), which implies this tool is for custom checks rather than built-in ones. However, it does not explicitly name alternatives or provide when-not-to-use guidance, so it stops short of a 5.

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