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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the set of lifecycle states, the fact that live user/RPS/p95/error-rate figures are only meaningful while running, and that a missing test_id silently falls back to the latest run. It stops short of saying whether finished runs remain retrievable indefinitely.

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?

Two sentences, zero waste. The core answer ('where a run stands') is front-loaded and the parenthetical merely enumerates the states and metrics rather than padding.

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 single-optional-parameter read tool with no output schema and annotations covering safety, the description supplies the state model and the no-argument default, which is nearly everything needed. The only meaningful omission is routing guidance relative to get_test_report.

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 100% and the schema already explains the test_id format ('the run id start_load_test returned'). The description goes beyond it by documenting the omitted-parameter default (latest run), which the schema does not state, so it earns above the 3 baseline.

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 names the resource (a load-test run) and its concrete states — building, starting servers, running, finished — plus the live metrics exposed while running, so the agent knows exactly what comes back. It does not, however, differentiate itself from get_test_report or start_load_test by name, so the sibling boundary is left to inference.

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 default-behavior rule ('Without a test_id it reports the latest run') is real usage guidance for the parameterless case. But there is no explicit statement of when to prefer this over get_test_report (e.g., polling during a run vs. fetching full results after), so usage is only implied.

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