Create baseline

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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds real value beyond them: it localizes the destruction to the replaceAll:true path, notes the portfolio refusal, and mentions 'One undo step' (reversibility). It does not give a return payload or what the new baseline looks like, but the output schema covers that, so this is close to complete.

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?

Four tight sentences, each earning its place: core action, the destructive flag path, sibling routing, and portfolio refusal plus undo. Front-loaded with the verb and the destructive caveat early.

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 two-parameter mutation with an output schema, it covers the action, the destructive branch, reversibility ('one undo step'), a domain restriction (no portfolio baselines), and how to reach related tools. Nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so the schema already documents both parameters. The description still adds meaning beyond the schema by attaching the destructive consequence to the replaceAll:true flag and clarifying that the created baseline is selected. This makes the flag's side effect explicit rather than just a boolean description.

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?

States a specific verb ('creates a baseline') and resource with concrete semantics: a snapshot of the current project state that also gets selected. It explicitly distinguishes itself from rillsoft_baseline_select and rillsoft_variance_report_get, so the agent can route between baseline siblings without opening schemas.

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?

Explicit when-to-use alternatives: switching baselines goes through rillsoft_baseline_select, comparison through rillsoft_variance_report_get. It also names a when-not condition ('Refused in a portfolio'), which no sibling sibling makes redundant. Nothing is left to inference.

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