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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description still adds information an agent cannot get from them: the return shape (descriptive counts plus alphabetical candidate examples), the negative guarantees (no efficacy, no treatment sequence), and the surprising detail that score and plausibility are null. That last point prevents wasted reasoning about empty fields,

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?

Roughly four sentences, all front-loaded: what it does, what it does not do, what the output looks like, where to go next. The alias note and the null-field warning each earn their clause because both prevent a specific agent error.

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 a full schema, a full output schema, and read-only annotations, the description covers everything the agent needs to decide and call correctly. The only residual gap is that it does not characterize what "registry evidence" actually draws from or how the optional filters alter the result set, leaving that entirely to the schema.

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 description coverage is 100%, so condition, stage, ageBand, markers and examples are already documented in the schema. The description adds no syntax, default or interaction detail beyond that (for example how markers combine with stage to narrow candidates). Baseline 3 is appropriate when the schema carries the parameter burden.

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 ("EXPLORE REGISTRY EVIDENCE for a condition") and immediately bounds the scope: it simulates nothing, returns descriptive counts and alphabetical candidate examples rather than efficacy or a treatment sequence. It also resolves the legacy alias simulate_twin, so an agent arriving with the old name still knows what it is. Read against siblings run_twin_experiment and twin_experiment_guide, the distinction is unambiguous.

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 closing "NEXT:" sentence names concrete alternatives and the condition that selects each: twin_experiment_guide / run_twin_experiment when explicit reaction-model simulation is wanted, post_reality_request when measurements are wanted. Combined with the explicit statement of what this tool does NOT produce, an agent can route without inferring anything.

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