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 behavior the annotations do not: that reports exist only for finished runs and that omitting test_id returns the latest run.

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 compact fragments, front-loaded with the primary purpose and the fallback behavior last. The content list is slightly dense but each item conveys return-value information in a tool with no output schema.

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 no output schema, the description carries the return-value burden and does so by enumerating verdict, users held, p95, error rate, bottleneck, and recommendations. The only minor gap is pagination/formatting behavior, which is unlikely to matter for a single-run 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 test_id's origin, so baseline is 3. The description adds meaning beyond the schema by explaining the optional-parameter default (latest run when test_id is absent), which the schema does not state.

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 concrete verb+resource (returns the report for a finished load-test run) and enumerates what the report contains, which separates it implicitly from get_test_status (in-progress) and start_load_test (initiation). It stops short of naming those siblings, so differentiation is inferred rather than stated.

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 phrase 'a finished run' implies this is the tool to use once a run completes rather than during it, and the no-test_id fallback is spelled out. There is no explicit when-not guidance or direct pointer to get_test_status for still-running tests, 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.