api_load_test

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

With no annotations, the description does real work: it caps requests at 200 and concurrency at 20, discloses what is reported (status counts, errors, latency percentiles), and flags the ownership/authorization caveat. It stops short of saying whether requests are fired all at once, whether it honors redirects, or how failures are counted.

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 tight sentences: the capability and its hard limits come first, the safety constraint last. No filler and nothing restates the tool name.

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?

An output schema exists, so return values need not be described, and the description still previews them plus the request/concurrency ceilings. It is nearly complete for a five-parameter tool, with only the unmentioned `method` and `timeout` semantics keeping it from a 5.

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 0%, so the description must carry the burden, and it only annotates two of five parameters: `requests` (max 200) and `concurrency` (max 20). `method`, `timeout` and the target `url` shape/format get no semantic treatment, leaving half the surface undocumented.

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: send N requests with C workers and report status counts, errors and latency percentiles. That outcome profile ('latency percentiles', 'status counts') makes it unmistakably a load probe rather than a single-request sibling like http_request or check_tcp_port.

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 only usage guidance is the caution 'Use only against systems you own,' which is a safety constraint, not a when-to-use rule. Nothing tells the agent when to pick this over http_request or run_command, so the selection logic is only implied by the word 'load probe.'

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