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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds that the result is a persistent Plan and that the brief is stored as brief.md, plus the duplicate-avoidance precondition. It never warns about the non-idempotent behavior (repeat calls create additional Plans) or permission requirements, which is the most valuable thing it could add 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?

Two sentences, front-loaded with the action and its preconditions, with zero filler. The final sentence about schedules and Fudge approvals is terse enough to be slightly ambiguous about what the caller should do instead.

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 five-parameter create tool with no output schema, the description establishes the trigger condition and the components of a valid Plan, which is enough to invoke it correctly. The main gap is that nothing tells the agent what comes back (plan identifier, created objects), and that must be inferred from the call result.

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 80%, so the schema already explains title, areas, brief and milestone notes, including limits and enums. The description only re-lists the field names and marks brief as optional. The 'store' parameter is not mentioned at all, so no meaning is added beyond the structured data.

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 and resource ("Start a new Plan") plus the payload it carries: title, areas, milestones, optional brief. The precondition "for a goal the merchant has agreed and no existing Plan covers" narrows scope beyond the bare name. It does not name any sibling (e.g. create_store_document or the create_draft_* family), so differentiation from adjacent create tools is left to inference.

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?

Gives a real when-to-use test: a goal the merchant has agreed and that no existing Plan already covers. The closing line about schedules and recurring work being "approved in Fudge" signals that scheduling is out of scope for this call. No explicit alternative tool is named for the overlapping case, which keeps it below a 5.

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