agent-lsp

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly describes the destructive nature of the operation ('discard', 'revert all in-memory changes'), the scope of impact ('restoring baseline content'), and the precondition ('when simulation results show the changes would introduce errors'). However, it doesn't mention potential side effects, error conditions, or what happens to the session after discarding.

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 perfectly concise with two sentences that each earn their place. The first sentence explains the action and effect, while the second provides clear usage guidance. There's no wasted verbiage or redundant information.

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 that this is a destructive operation with no annotations and no output schema, the description does a good job explaining the core behavior and usage context. However, it doesn't mention what happens after discarding (e.g., whether the session becomes unavailable, what the response looks like, or error conditions). For a tool with such significant impact, more complete behavioral context would be helpful.

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 description coverage is 0%, but the description doesn't provide any information about the 'session_id' parameter beyond what's implied by context. While the description is clear about what the tool does, it doesn't explain what a session_id is, how to obtain it, or its format. The baseline is 3 since the description doesn't compensate for the schema coverage gap.

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 clearly states the specific action ('discard a simulation session') and the effect ('revert all in-memory changes by restoring baseline content'), distinguishing it from siblings like 'destroy_session' or 'commit_session'. It uses precise verbs and specifies the resource being acted upon.

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 description explicitly states when to use this tool: 'Use when simulation results show the changes would introduce errors.' This provides clear context for invocation and differentiates it from alternatives like 'commit_session' (which would preserve changes) or 'destroy_session' (which might have different semantics).

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