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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false), and the description adds genuinely non-redundant behavior: it may silently create a new project when project_id is omitted, and it returns the project plus links, the plan's kickoff message, and the skills to load. That side-effect and post-call requirement disclosure is what an agent most needs here.

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 core action and the plan-ref taxonomy are front-loaded, but the single paragraph is dense and repetitious — the nature of a plan is restated, and the accepted-ref list duplicates the schema description almost verbatim. It would read better as separated sentences for what it does, when to use it, and what it returns.

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, the description carries return-value burden and does so: project, links, kickoff, and skills to load. Defaults for inputs and workspace are covered. The only remaining gap is the relationship to open_project/create_editor_project, but for a 4-param tool this is close to sufficient.

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 baseline is 3; the description exceeds it by explaining the accepted ref forms for `plan` and the consequence of supplying vs. omitting `project_id` and `workspace_id` (workspace only matters for the new-project path). It adds little on `inputs` beyond what the schema already says about defaults.

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 makes clear this instantiates a plan (a personal template ref, a getPlan.md slug/address, or a kit's plan) and returns the resulting project. The verb is softened to 'Takes plan', but '[write]' plus 'Returns the project and its links' disambiguates it from read-only siblings like read_project or list_templates. Sibling differentiation is implied rather than stated (open_project is never mentioned).

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 gives an explicit trigger condition: 'Use it when the person names a getPlan.md plan or a kit's plan, or pastes an address', and explains the project_id decision rule (existing footage → supply project_id; otherwise a new project is made). What's missing is a direct contrast with open_project for the case where no plan is involved.

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