Learned Patterns

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the read-only nature is well covered. The description adds the scope (per repository) and the subject (false-positive patterns learned by ARGUS), which is mildly useful. It doesn't describe output format or ordering, but that's less critical for a listing tool with strong annotations.

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 a single, clear sentence with no wasted words. It front-loads the action and subject effectively.

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 simple read-only listing tool with one well-documented parameter and strong annotations, the description is adequate. It could benefit from mentioning what the output contains (e.g., pattern IDs, suppression rules) but this is a minor gap given the available annotations and schema.

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 covers 100% of the parameter (path) with a description, so the description doesn't need to add much. The tool description implies the path is the repository root, which aligns with the schema. Baseline 3 is appropriate as the schema handles the meaning.

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: to list false-positive patterns learned by ARGUS for a repository. The verb 'List' and resource 'false-positive patterns' are specific, and it distinguishes itself from related tools like learn_false_positive (which likely learns patterns) and memory_scan/memory_get (general memory). However, it doesn't explicitly name siblings to differentiate, dropping from a 5.

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 the tool is for viewing learned patterns, but it doesn't explicitly state when to use it versus alternatives like learn_false_positive for adding patterns. The context is clear, but no exclusions or alternative selection criteria are given.

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