bernstein_task_handle

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

With no annotations, description carries full burden. It discloses stateless polling, audit-chain head embedding, path traversal refusal, and that the handle is a projection. No contradictions. Minor omission: no error scenarios mentioned.

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?

Description is well-structured with purpose sentence, behavioral details, then Args and Returns sections. Every sentence adds value; no fluff. Front-loaded with core purpose.

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 moderate complexity and presence of output schema (mentioned in Returns), description covers purpose, parameters, and behavior adequately. Missing error cases or prerequisites. Overall complete for a handle-retrieval tool.

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?

Description adds significant meaning beyond schema (which only has types). Args section explains run_id must be plain identifier with no path separators, and workdir defaults to current directory. Schema coverage 0% but description fully compensates.

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 clearly states 'Return a verifiable Tasks-extension handle for a run, by run id', specifying the verb (return) and resource (handle). It distinguishes from siblings like bernstein_status by emphasizing verifiability and audit integration.

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?

Description implies usage through stateless polling and projection but does not explicitly state when to use this tool over alternatives (e.g., bernstein_status, bernstein_tasks). No exclusions or when-not-to-use guidance.

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