test_agent_tool

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the agent knows this makes external calls and is not a safe repeatable read. The description adds useful context that execution runs through the live agent runtime via WebSocket toolTest mode, but it never states what 'generate-and-test' actually creates or mutates (e.g. whether the tool definition is written), nor what happens on timeout. That is the key behavioral fact the annotations leave open.

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 tight sentences, front-loaded with the core action and followed by two sibling-disambiguation clauses. No filler and nothing repeated from structured 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?

A 7-parameter, runtime-executing test tool with no output schema needs the description to cover parameter roles and result expectations. Routing and purpose are complete, but the description never says what validate versus generate-and-test returns or why convoId/message/timeoutMs matter, leaving real gaps for an agent configuring a call.

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 description coverage is only 14% — six of seven parameters have no schema-level documentation. The description only illuminates the mode enum (validate | generate-and-test), and even then not what each mode does. It says nothing about agentId, toolId, toolName, convoId, message or timeoutMs, including the important distinction between toolId and toolName, which are both required.

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?

Names a specific verb and resource (test an agent HTTP tool) plus the exact execution path (interact WebSocket toolTest mode through the agent runtime) and the two modes. It also explicitly distinguishes itself from the two nearest siblings, so an agent can separate this from test_agent_tool_request and run_agent_auto_test without opening either schema.

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?

Gives explicit routing rules: use test_agent_tool_request for a direct HTTP dry-run against serverUrl, and run_agent_auto_test for multi-turn suites. Both alternatives are named with the condition that selects them, which is exactly the guidance an agent needs to pick correctly among three overlapping testing tools.

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