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

Beyond the readOnly/openWorld/idempotent annotations, it discloses the paid cost model ($0.001 USDC per call on Base via x402), the exact retry mechanism with params._meta["x402/payment"], the 400 error case, and paging via nextPageToken. These are precisely the operational facts an agent needs that annotations cannot express.

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?

Front-loaded with purpose and filters, then returns, then errors and payment — a sensible ordering. The long enumeration of return fields is dense but compensates for the absent output schema; only slight tightening would be possible.

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 10-parameter, zero-required, open-world search with no output schema, the description covers purpose, filter surface, return shape, pagination, errors and payment. Missing pieces are minor: defaults for limit/sort and filter combination semantics.

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?

With 60% schema description coverage, the description usefully maps friendly concepts to parameters (intervention/drug, sponsor, location, phase, status) and mentions the paging token, but adds nothing about sort ordering, the limit default/cap, or whether multiple filters are ANDed. Baseline 3 is right given the schema does most of the work.

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+resource (search ClinicalTrials.gov studies) and enumerates the filterable dimensions — condition, intervention/drug, sponsor, location, keyword, status, phase — which clearly separates it from the sibling clinical_trial_study (single-study retrieval). It never explicitly names that sibling as the alternative, so it stops short of a 5.

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?

'Useful for trial finding, pipeline and competitive research' gives implied usage context, but there is no explicit when-not guidance or routing rule such as 'use clinical_trial_study once you have an NCT ID'. Prerequisites (e.g., at least one filter to avoid a broad scan) are also unstated.

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