nemesis_run_learn

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

While annotations indicate non-read-only and open world behavior, the description adds specifics: 'locally' scopes the execution, and the token requirement ('needs the app token (nsk_)') is disclosed. This clarifies the prerequisites and reduces ambiguity about external effects.

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, front-loaded with the verb, no redundant words. Covers purpose, usage context, and token requirement efficiently.

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 run tool with no output schema, it explains the workflow, environment, and follow-up tools. It doesn't describe return values, but that's acceptable given no output schema and clear purpose.

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 covers all parameters with 100% coverage, so description contributions are bonus. It adds the env var fallback ('set NEMESIS_TOKEN in the env') for appToken, giving extra semantic detail beyond the schema.

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 'Run the Nemesis Learn agent locally to exercise every route of your app', specifying the action, resource, and goal. It differentiates from siblings by focusing on the Learn agent for route exercising, distinct from scanning or protecting.

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?

It provides context: use this in dev/staging to speed up baseline creation 'instead of waiting on real traffic'. It also gives follow-up steps ('Then call nemesis_approve_routes and nemesis_set_mode enforce'), though it doesn't explicitly list when not to use it.

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