retrieve_performance

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

With no annotations provided, the description fully discloses the async behavior: the server returns immediately with a pending/running status, the final result must be fetched via a separate tool, and retry behavior is explained. It also details the pendingReason semantics and what to report to the user, giving deep behavioral context beyond the basic action.

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 fairly long but every sentence contributes necessary information about the async workflow and edge cases. It is front-loaded with the core purpose, then systematically explains the return payload, companion call, and pendingReason behaviors, so the length is justified and well-structured.

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 (async workflow, no output schema, no annotations), the description covers everything needed: the immediate return payload, how to retrieve the final result, duplicate-work warning, and handling of both pendingReason cases. It is complete for an agent to use the tool correctly.

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 tool has zero parameters, so schema coverage is effectively 100% and the description adds no parameter detail. The baseline of 4 is appropriate because no parameter explanation is needed; the description instead focuses on the workflow and return value semantics.

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 states the tool retrieves performance analytics from the LinkedIn dashboard, using a specific verb+resource construction. It is distinct from sibling retrieve_* tools like retrieve_connections or retrieve_ssi by naming the specific analytics domain.

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 provides explicit usage guidance: it tells the agent to call get_workflow_result with the returned workflowId and operationName, warns against retrying the original tool while the workflow is running to avoid duplicate work, and explains how to handle different pendingReason values including queueing and outside working hours.

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