research_cancel

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

With no annotations to rely on, the description fully discloses behavior: terminal-run behavior (cancel_requested: false, no RPC), non-terminal behavior (cancel_requested: true, run_status_before), replication-lag edge case, and fire-and-forget semantics. This is exceptional transparency.

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 concise yet comprehensive, organized into three short paragraphs: purpose, parameters, and behavioral details. Every sentence adds essential information with no filler.

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 and lack of annotations, the description covers all key aspects: what it does, required parameters, edge cases, return flag semantics, and next steps. An output schema exists, but the description still adds value by explaining the cancel_requested flag and statuses.

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 coverage is 0%, so the description must explain parameters. It does so thoroughly: notebook accepts name/ID, poll_task_id comes from research_start/research_status, and run_id is a deprecated alias. All three parameters are semantically covered.

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 opens with a specific verb+resource: 'Cancel an in-flight research run in a notebook.' This clearly distinguishes it from siblings like research_start and research_status, which are explicitly mentioned for context.

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 states the main use case (cancel in-flight research) and gives a follow-up guideline: 'Fire-and-forget; poll research_status afterward to confirm.' It does not explicitly exclude alternatives, but the context and mention of related tools make usage clear.

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