brain_graph

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

With no annotations, the description carries the full burden. It does disclose useful behavior: a server starts on localhost, a URL is returned, and the graph updates live with Replay animation. It omits what happens if the graph is already running, whether the server persists or how to stop it, and any port or blocking behavior — meaningful gaps for a process-spawning tool.

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 short sentences, front-loaded with the action and result, then the user-facing instruction. The trailing clause about nodes popping in and Replay is partly flavor but conveys real runtime behavior, so it mostly earns its place.

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 zero-parameter tool with an output schema, the description covers the action, the localhost URL return, and what to do with it. The only notable omission is repeated-invocation behavior (what happens if the graph is already running) and its relationship to pause_brain/resume_brain.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description does not need to explain any inputs.

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 live, animated brain graph served on localhost and return its URL. That is clearly distinct from siblings like brain_status (text status) or rebuild_brain (data rebuild). It stops short of naming a sibling explicitly, so it lands at 4 rather than 5.

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?

Usage is only implied: an agent can infer this is for when the user wants a visual/animated view, and 'Give the user the link' is a concrete post-call instruction. There is no explicit when-not guidance or routing to alternatives such as brain_status or pause_brain/resume_brain.

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