bernstein_complete

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

No annotations provided, so description carries full burden. Discloses that tool reads task first, only completes from states 'open', 'claimed', 'in_progress', and refuses other states with structured errors. Also notes empty summary is rejected and fails the task. Some behavioral details like permissions or rate limits are omitted, but the core behavior is well described.

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?

Well-structured with clear paragraphs and bullet-like lists. Every sentence adds value, no redundancy. Concise yet comprehensive, using backticks to reference sibling tools and schema fields.

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 complexity of the workflow and presence of output schema, the description covers state machine constraints, error behavior, and expected return format. It also addresses edge cases (orphaned, waiting_for_subtasks, refusal). Complete enough for correct usage.

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?

Input schema has 0% description coverage, so description must compensate. It does so effectively: defines task_id as 'ID of the task to complete' and result_summary as 'What the work produced', and explicitly states that empty summary is rejected. This adds essential context beyond basic schema 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?

Clearly states the tool's purpose: 'Report the result of work you are executing.' Explains it is the completion verb in the MCP worker loop, distinguishing it from siblings like bernstein_claim, bernstein_update, and bernstein_approve.

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?

Explicitly describes when to use: after bernstein_claim and bernstein_update, to finish a task. Also states when not to use: for clearing parent/orphaned tasks or signing off results, with specific alternatives provided (bernstein_update, bernstein_approve). Includes caution to report only work that actually ran.

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