parseltongue_clear_session

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

The description states that the tool 'clears all state' while 'keeping the session alive', which clarifies that this is a destructive operation on session content (not the session itself). It also states the return format (JSON with clear status). However, with no annotations provided, the description could add more behavioral context such as whether this is reversible, what 'all state' includes (registered documents, loaded DSLs, etc.), and any side effects on future operations.

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 compact and follows the Args/Returns structure, covering the essential purpose in minimal words. The front-loaded first sentence clearly states the core behavior. It earns high marks for efficiency, though the Returns line is marginally useful as it just restates that a JSON status is returned.

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 single-parameter tool with an output schema, the description is reasonably complete. The first sentence distinguishes the destructive scope (clear all state) from session lifecycle (keep alive). However, given the sibling tools like register_document, load_dsl, and get_state, the description could clarify what 'all state' covers (e.g., does it clear loaded DSLs, registered documents, query history?) to help the agent understand full impact.

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 description coverage is 0%, so the description must compensate. It names session_id in the Args section, which adds a small bit beyond the schema (the schema only has a type and title). However, it doesn't provide extra context about what session_id must refer to (e.g., a session created by parseltongue_create_session) or whether it accepts any valid session ID. With only a single, self-explanatory parameter, the marginal gap is modest.

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 tool's purpose: 'Clear all state from a session, keeping the session alive.' This uses a specific verb (clear) with a specific resource (session state) and adds the important nuance that the session itself persists. It's distinct from siblings like get_state (read) and create_session (lifecycle), though it doesn't explicitly name those distinctions.

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 implies usage context: it's for when you want to reset a session's contents without destroying the session. It doesn't explicitly state when NOT to use it or offer alternatives (e.g., 'use parseltongue_create_session for a fresh session' or 'use parseltongue_query to review state first'). Given the sibling set, there's room for more explicit guidance on when this is the right choice versus creating a new session.

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