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

Beyond the readOnlyHint and non-destructive annotations, the description discloses a key behavioral trait: the list intentionally omits effect sizes due to measurement integrity, and it also returns the additional 'namedUnmodellable' payload. It even explains the sibling's withholding behavior, giving the agent a complete picture of what this endpoint does and does not return.

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 longer than average but every component earns its place: it clarifies scope, data fields, a public URL analogy, the namedUnmodellable extra return, and the critical no-effect-sizes caveat. It is front-loaded with the core purpose and uses punctuation to group details effectively.

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 an output schema present and no parameters, the description covers everything an agent needs: what is returned, the number and nature of models, key fields, the important absence of effect sizes, and the route to a sibling tool for richer data. This is fully self-sufficient for correct invocation.

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?

The input schema is empty, so there are no parameters to document. Baseline for zero parameters is 4, and the description adds no irrelevant parameter detail, which is appropriate.

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 uses a specific verb ('List') and names a concrete resource ('constructed outcome-model register behind Performix diagnostics'), then enumerates the fields each model carries. It also distinguishes itself from the sibling get_outcome_model by stating that this list has no effect sizes and directs the agent to get_outcome_model for a driver table.

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?

It explicitly states when to use the alternative: 'call get_outcome_model for a driver table' and explains that this list 'carries no effect sizes at all,' making the choice between list_outcome_models and get_outcome_model unambiguous.

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