list_research_tasks

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

Beyond 'readOnlyHint' annotation, description discloses that list status is approximate and 'running' covers queued/reconciling tasks, providing important behavioral context. No contradictions with annotations.

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 sentences, no redundancy. Front-loaded with purpose, followed by key features and a caveat. Every sentence adds value.

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?

With output schema present, description needn't detail returns. Covers pagination, filtering, status approximation, and directs to sibling for authoritative status. Sufficient for a list tool with simple parameters.

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 description must compensate. Mentions 'cursor pagination and status filtering', giving context for limit, cursor, and status parameters. However, does not detail each parameter's syntax or behavior (e.g., cursor format, limit bounds). Partial compensation raises score from baseline 1 to 3.

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 explicitly states it lists one-time research tasks for the authenticated user, uses specific verb 'list' and resource 'research tasks', and distinguishes from sibling 'get_research_task_result' by noting the approximate status.

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?

Clear context for use: list tasks with pagination and status filtering. Explicitly advises to use 'get_research_task_result' for authoritative status, indicating when not to use this tool. Differentiates from 'list_browsing_tasks' and 'run_research_task' siblings.

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