self_patterns

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

Annotations already cover read-only and idempotent behavior. The description adds value by detailing what data is analyzed (error patterns, insight candidates, rule effectiveness, trends) and the periodic cadence. No contradiction; the description enriches the annotation-provided safety profile.

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, zero fluff. The main purpose is front-loaded, and the view list is compactly presented. Every word contributes to the tool's functionality.

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?

The description covers the core functionality and views well, but omits details about the 'project' parameter and does not describe the output format. Given the tool has 3 optional parameters and no output schema, these gaps make it adequate but not fully complete.

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?

With 0% schema coverage, the description must explain parameters. It fully explains the 'view' enum values, but does not explain 'days' (only hints via 'weekly errors') or 'project' at all. It adds meaning for the primary parameter but leaves two parameters under-documented.

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?

Description states a specific verb ('Analyze') and resource ('error patterns and self-improvement stats'), then enumerates five distinct views that define exactly what analyses are available. This clearly separates it from sibling tools like self_error_log (logging) and self_reflect (general reflection).

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 suggests periodic invocation ('Call periodically to track improvement'), implying a monitoring use case. It does not explicitly name alternatives or exclusion criteria, but the view list implicitly differentiates from other self-* tools. This is clear context without formal when-not guidance.

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