cos_learn_extract

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

Annotations indicate a non-read-only, idempotent operation. The description adds a concrete side effect: inserting new patterns into learned_patterns with calculated confidence. It does not contradict the annotations and provides useful behavioral context beyond them.

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 concise and well-structured, with a clear purpose, effect, args section, and return type. It contains no redundant information and each sentence serves a purpose.

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 single-parameter tool with an output schema, the description covers the core aspects: purpose, detected patterns, insertion behavior, parameter meaning, and return format. It could be more detailed about the analysis stats, but is largely complete given the available structured data.

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 description coverage is 0%, but the description explains the only parameter (min_occurrences) as the minimum occurrences to consider a pattern, with a default of 3. This adds meaningful semantic information beyond the raw schema type and default.

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 it scans task outcomes to discover recurring patterns, listing specific pattern types (domain_rework, skill_correlation, complexity_mismatch). It also mentions inserting into learned_patterns, distinguishing it as an extraction/write tool, though it doesn't explicitly compare to sibling learning tools like cos_learn_suggest.

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 usage for discovering patterns from task outcomes, but provides no explicit guidance on when to use this tool versus alternatives such as cos_learn_suggest or cos_learn_validate. It lacks exclusions or alternative recommendations.

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