start_project

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds useful context that state is persisted server-side and survives sessions, but it omits traits like whether repeated calls create duplicate projects or what side effects occur on the server.

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 tight sentences; the core action is front-loaded and the follow-up session guidance follows immediately. No filler.

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?

An output schema exists so return values need no explanation, and the persistence model plus continuation path are stated. Only minor gaps remain around idempotency and side effects of project creation.

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 86%, so parameters like workflow, goal, addon, steps and inputs are largely documented already. The description adds only an indirect hint (project_id exists as an output consumed by next_step) and says nothing extra about workflow/steps semantics.

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 persistent orchestration project') plus what it returns ('the first ready step(s)'). It also names the continuation sibling next_step(project_id), so an agent can separate this from list_projects/get_project/next_step without opening any schema.

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?

Implies the when: begin a new orchestration project and hand back the first actionable step; and it explicitly routes continuation to next_step(project_id). No explicit exclusions (e.g., when to resume vs. start fresh, or how this differs from list_projects) are given.

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