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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clarifies that this tool returns only experiment IDs rather than full experiment data, and the 'Discovery:' label signals a read-only, exploratory operation. It does not mention ordering or pagination, but the output schema can cover those details.

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?

The description is a single, focused sentence with no filler. The key action 'list' and scope 'recorded benchmark experiment IDs' are front-loaded, and the reference to cognitive.get_experiment is immediately useful.

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?

The tool is a simple zero-parameter list operation, and an output schema is already present. The description adequately explains what the tool returns and how it relates to sibling tools, so an agent has enough context to select and invoke it correctly.

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?

There are zero parameters, and the input schema is empty with 100% schema description coverage. The description adds context by specifying the output is limited to benchmark experiment IDs, which is sufficient for a parameterless tool.

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 starts with 'Discovery:' and clearly states 'list recorded benchmark experiment IDs for cognitive.get_experiment.' It uses a specific verb and resource, and explicitly references the sibling tool it supports, making it easy to distinguish from cognitive.get_experiment and other siblings.

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 'for cognitive.get_experiment' provides clear context that this tool is used to discover IDs for later retrieval. It does not explicitly state when not to use it or name alternative discovery methods, but the intended usage is clear from the description.

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