ampl_restart_session

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

The description discloses the key destructive behavior: 'discarding all model state.' However, with no annotations provided, it fails to mention other important behavioral aspects such as whether the session is closed, if data/files need reloading, or any side effects on other resources. It is minimally transparent.

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 description is extremely concise: one sentence plus a brief phrase. It front-loads the action ('Restart the engine') and adds a clarifying effect ('discarding all model state'). Every word adds value with no redundancy.

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 destructive operation with no annotations and an unexplained parameter, the description is incomplete. It does not explain recovery steps, prerequisites, or full consequences (e.g., what state is exactly lost). The output schema might help, but the description alone leaves crucial context missing.

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 schema has one optional 'name' parameter with 0% description coverage. The description does not mention this parameter at all, leaving its purpose and allowed values completely unexplained. Since schema coverage is low, the description should have compensated but did not.

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?

Description explicitly states 'Restart the engine, discarding all model state' – a specific verb (restart) and resource (engine), with the effect clearly described. This distinguishes it from sibling tools like init/close/eval by focusing on restarting rather than creating or modifying.

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?

The phrase 'The recovery path' implies use for recovery scenarios, but there is no explicit guidance on when to use this tool vs alternatives (e.g., close_session + init_session) or prerequisites like having an active session. It hints at usage but does not state it clearly.

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