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

Annotations declare readOnlyHint=true, and the description does not contradict this. The description adds valuable behavioral context beyond the annotation: it explains the conditional behavior based on `node`, the distinction between anonymous callers and project callers (free tier vs project's own data), and that certain parameters are ignored for projects. This is useful transparency about how the tool behaves in different contexts.

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 compact and front-loaded. The first sentence states the core purpose. The second sentence explains the conditional behavior. The third sentence covers the auth/context distinction. Every sentence earns its place, and there is no redundant repetition of schema details. The structure is logical: what, when, and how it behaves.

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?

Given the tool's moderate complexity (conditional behavior, free-tier vs project distinction) and the absence of an output schema, the description covers the key aspects an agent needs: what the outline contains, what a node returns, and how parameters are scoped. It doesn't explicitly describe the output format (e.g., JSON structure), but the description's mention of 'phases and objectives with step counts' and 'every step under it, with status and whether it is unlocked' gives a reasonable picture. The sibling tools (get_step, get_directory) suggest this is part of a family, and the description is sufficient to select this tool correctly.

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 100%, so the schema already documents all parameters. The description adds meaning by explaining the role of `node` (phase/objective slug) and how `done`, `not_applicable`, and `traits` are used in the free tier vs ignored for projects. This goes beyond the schema's individual parameter descriptions, which don't mention the free-tier/project distinction. The description doesn't repeat the enum values, which is appropriate since the schema covers them.

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 function: retrieving the launch plan, with a distinct behavior depending on whether a `node` parameter is provided. It distinguishes between the outline view (without `node`) and the detailed step view (with `node`), and it names the specific fields returned (status, unlocked). This is a specific verb+resource description that differentiates it from siblings like get_step and get_directory.

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 provides clear context for when to use the tool: to get the launch plan outline or a specific node's steps. It implicitly differentiates from siblings by describing the two modes. However, it does not explicitly state when NOT to use it or name alternative tools (e.g., get_step for a single step, get_directory for directories). The guidance is clear for the tool itself but lacks explicit exclusions.

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