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

With no annotations, the description carries the full burden of behavioral disclosure. It effectively communicates safety limits (100 connections, 5 min duration, 1 test at a time, 60s cooldown), permission requirements (OWNER/ADMIN only), and mode-specific tooling (autocannon, Playwright). It stops short of describing response behavior or error scenarios, but covers critical operational boundaries.

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?

Four dense, purposeful sentences. Each sentence adds distinct information: action, limits, modes, and permissions. No fluff or repetition; front-loaded with the primary purpose.

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 complex 8-parameter tool with no output schema, the description covers key operational constraints, permissions, and modes. It doesn't elaborate on each parameter but the schema does. It could mention the response shape or next steps (e.g., get_load_test), but the description is sufficient for starting a load test.

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% so baseline is 3. The description adds value by explaining mode enum values with underlying tools and mentioning real-world constraints (cooldown, one-at-a-time) not present in the schema. It also reinforces concurrency and duration limits aligned with schema min/max.

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 opens with 'Start a load test against a target', using a specific verb and resource. It clearly distinguishes from sibling tools like cancel_load_test or get_load_test by focusing on the initiation action, and further details modes and constraints.

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 description provides clear operational context: max concurrency, duration, single test per target, cooldown, modes, and OWNER/ADMIN permission. It does not explicitly state exclusions or compare directly to alternatives like trigger_test, but the limits and constraints give strong usage guidance.

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