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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent operation, all local. The description adds the returned fields (testId/status/score) and the mode set, which is useful. It does not say whether the run is synchronous or whether testId must be polled elsewhere, nor anything about runtime/cost for long suites — the most important ambiguity for a "start" operation.

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 short sentences: what it does, what it returns, and the routing hint, all front-loaded with no filler. The endpoint reference is compact and useful rather than wasted.

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?

For a nested-config, no-output-schema tool, the description covers purpose and return fields well enough to attempt a call with only agentId. But it leaves the async/sync question open and does not explain the config knobs an agent would need to run a meaningful regression mode.

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 0% and the config object has six nested properties, yet the description only touches testMode — and even then lists four modes while the enum has six (prompt-only and with-kb are omitted). agentId, enableKB, maxTurns, naturalEnd, testScenario and enabledToolIds get no explanation at all.

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?

States a specific verb and resource ("Start Convocore automated agent test suite") and even pins the underlying endpoint (POST /auto-test/run). It distinguishes itself from the sibling test_agent_tool by scope, so the agent can pick it without opening the 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?

"Prefer this for broader regression; use test_agent_tool for a single tool" names the alternative and the condition that selects it. There are no exclusions or prerequisites (e.g. agent must exist/be published) beyond that, but the core routing decision is explicit.

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