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

The description discloses non-obvious behaviors beyond the annotations: it counts trial existence as an upper bound, groups by normalized intervention name, includes an explicit censoring rule, and reports numerator/denominator for auditability. This gives the agent a clear mental model of how results are derived and how to interpret them.

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 long but every sentence carries substantive information: core purpose, method, example use cases, output shape, and an important caveat. The single dense paragraph is somewhat less scannable than it could be, but there is no fluff or redundant repetition.

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 no output schema, the description compensates well by specifying that output includes transition rates as numerator/denominator, a benchmark comparison, and top interventions with per-phase trial paths for auditability. Combined with a fully documented schema and strong annotations, an agent has all essential information to invoke and interpret the tool.

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%, with each parameter already documented including defaults, ranges, and behavioral effects (e.g., censor_years shrinking the denominator). The description reinforces this context but does not add substantial new parameter semantics beyond what the schema provides, so the baseline 3 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 names a specific analytic verb ('Measure') and resources ('clinical phase transition rates', 'registry-derived analog'), then gives concrete example questions that make its scope unmistakable. It also contrasts this tool with efficacy or approval metrics, differentiating it from sibling tools like ct_results_summary or ct_get_study.

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 provides explicit example questions ('what fraction of Phase 2 assets in NSCLC reach Phase 3', etc.) and states when the tool is appropriate for PTRS/attrition analysis. It also clarifies that it counts trial existence rather than success, which guides interpretationresident. However, it never names alternative sibling tools or gives 'use this instead' disambiguation, so it stops short of fully explicit routing guidance.

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