restart_session

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

With no annotations provided, the description carries the full burden and does well: it discloses the destructive side effect ('The loaded design and any constraint changes are lost') and the necessary follow-up ('call load_design again'). It does not mention whether the restart requires specific permissions or how long it takes, so it falls just short of a 5.

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?

Three sentences, each earning its place: one states the action, one states the consequence and required follow-up, one states the trigger condition. Front-loaded with the core action; 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?

Given no annotations, zero parameters, and complexity from the destructive nature of the operation, the description covers all an agent needs: what it does, what is lost, what to call afterward, and when to use it. An output schema exists, so no return-value details are required.

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?

Zero parameters, so the baseline is 4. The description appropriately adds nothing about parameters because there are none, and the schema is trivially complete. No parameter-related content is needed or missing.

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+resource: 'Stop the sta process and start a fresh one.' The agent knows exactly what this does, and it is clearly distinguishable from siblings like get_status (read state), load_design (load design), and run_tcl (execute commands).

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 an explicit when-to-use condition: 'Use this after get_status reports sta as exited, stalled, or holding an unfinished command.' It names the sibling tool to check first and enumerates the trigger states, leaving no ambiguity about when to invoke restart_session rather than other tools.

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