expand_around

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

Without annotations, the description must fully disclose behavior. It only states the action and result type, but omits side effects, safety profile, permissions, or what qualifies as a 'turn'. The term 'raw' is vague.

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 a single sentence, which is concise but overly terse. It could include essential parameter relationships without becoming lengthy.

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 the tool's complexity (4 parameters, required uuid and session_id) and lack of annotations, the description is insufficient. The output schema may partially compensate, but the description should explain the anchor concept more clearly.

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 description does not explain any parameters (uuid, session_id, after, before). With 0% schema description coverage, the agent receives no semantic help beyond parameter names and types.

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 specifies the tool returns raw turns around an anchor, listing the content types (tool calls, outputs, thinking). It distinguishes the tool's purpose from siblings like grep or recall_search, though it could explicitly contrast them.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., grep for searching turns, step for navigation). The description lacks contextual hints for triggering conditions.

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