unstick_session

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

No annotations are provided, so the description carries full disclosure burden. It explains the destructive actions (scrubbing content, dropping files) and the required post-step. This level of detail is good for a recovery tool, though it could mention whether changes are reversible.

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 concise sentences: first states purpose, second lists actions, third gives user instruction. No unnecessary words, well-structured.

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?

Despite no output schema, the description mentions that the tool reports what was changed. All parameters are covered. The post-action instruction completes the context. No critical gaps.

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 100%, so the base is 3. The description adds value by explaining that omitting session_id uses the most recently modified session, which is not in the schema. The no_backup parameter is already clear in the schema.

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 unsticks a Claude Code session stuck on 'PDF too large' / 'Image too large' errors. It explicitly describes the actions: scrubbing oversized base64, dropping warning state files, and reporting changes. This distinguishes it from sibling tools like recover_session and clean_claude_directory.

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 specifies when to use the tool (when a session is wedged on specific errors) and provides a clear post-action instruction (user must start a new conversation). While it does not explicitly mention alternatives, the context is sufficient for the agent to decide when to invoke this tool.

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