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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context about credential handling and the guarantee that credentials are never placed in URLs or echoed in errors, but it never explains what 'starting a test' actually does or what state it mutates.

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 compact sentences, front-loaded with the action, and the security guarantee in the final sentence earns its place. The unexplained 'P3' term is the only real waste.

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 destructive, non-idempotent mutation tool with no output schema and 33% parameter coverage, the description omits what starting the test produces or destroys and what success looks like. The credential guidance is helpful but does not fill the core behavioral gap.

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 only 33% and only the credential parameter has a schema description. The description usefully clarifies that the credential may be passed as an argument or via the Authorization header (beyond the schema), but it leaves slug and version_id semantics to the schema's bare patterns.

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 verb 'Start' is clear and the phrase 'on your own exact immutable version' ties the action to the version_id parameter, but 'P3' is unexplained jargon that leaves the actual resource ambiguous. It does nothing to differentiate itself from siblings like author_test_state, author_test_replay, or author_status.

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 says how to supply credentials but never states when to use this tool versus alternatives such as author_status or preview_author_step. No prerequisites or preconditions (e.g. whether a version must be prepared first) are given.

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