learn_patterns

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to mention whether the operation is read-only, what it returns, how long it might take, or any side effects. The only behavioral hint is the broad scope ('ALL projects'), which implies potential cost, but no details are given.

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, efficient sentence that leads with the action ('Scan ALL projects') and lists the key subjects. It avoids fluff, though the final clause 'Claude uses this to build better' is somewhat promotional and could be omitted. Overall, it is concise and front-loaded.

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?

With no output schema, no annotations, and zero parameters, the description is the sole source of context. It fails to explain what the tool returns (e.g., a summary, report, or learning embedded in the agent), how the results are used, or any prerequisites. This is especially inadequate for a tool that scans all projects, as agents might need to know about performance or outcome format.

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 tool has zero parameters and the input schema is effectively empty (100% schema coverage). The description correctly adds no parameter documentation because none exist. A baseline of 4 is appropriate since there is nothing to confuse an agent about arguments.

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 scan all projects and learn the developer's patterns, explicitly listing the kinds of patterns (frameworks, stacks, architecture, strengths). It distinguishes itself from sibling tools like list_projects and search_projects by focusing on pattern extraction rather than listing or searching individual projects.

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 context by stating 'Claude uses this to build better,' which suggests it should be used when the agent needs to tailor its output to the developer's style. However, it does not explicitly mention when NOT to use it or point to alternative tools, so guidance is incomplete but still reasonably clear.

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