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

The description goes well beyond the annotations: it discloses that the call is served locally (no board-core route, direct call gets 404), that it publishes an `agent.run` event, that subsequent calls belong to the run, and that personal tokens get a 200 with `run_key: null`, `logged: false` and no error. This is genuinely useful behavioral context that the readOnlyHint/destructiveHint flags do not convey. It is thick but not exhaustive about the success payload.

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 statement is front-loaded, but the title is duplicated verbatim at the start of the description and the spec/route asides (D144, x-mcp-local, D176) add bulk. It is informative rather than padded, yet a tighter opening sentence would let the routing detail sit as a second paragraph.

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 one-parameter, non-destructive tool with no output schema, the description covers intent, the implicit-run alternative, the local-routing quirk, and the personal-token no-op path. It implies a `run_key` is returned but does not describe the success response shape, which is the only notable gap.

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% and the single `goal` param already has a description and example, so the baseline is 3. The description adds meaning by tying `goal` to the published `agent.run` event and to the run-log format, clarifying what the value is used for rather than just its type.

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 states a specific verb and resource — start a new run with a goal — and explains the intent (the run log reads "goal → what you did and why"). The purpose is clear, but the leading spec-reference framing and the repeated title text make the agent dig slightly for it. No sibling tool covers runs, so differentiation is not an issue.

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 explicitly notes the tool is optional and that a run also starts implicitly via a new MCP session or after 15 minutes idle, which gives the agent a real when-to-use/when-not signal. It stops short of stating the positive trigger as directly (e.g. "call this when you want an explicit goal recorded before a multi-step task").

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