Clinical Trial Leads: Sponsors, Sites & Contacts

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

Beyond the annotations (readOnly, openWorld, non-idempotent, non-destructive), it discloses that the tool executes an Apify Actor on the caller's own account, the exact price ($0.002/trial), that zero-result runs are free, the hard spend cap, and the run_max_charge_usd default. It also warns that maxResults set above run_max_items can bill more than is returned, and gives latency expectations and timeout remediation.

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, then differentiation, then usage, then parameters, then a clearly labeled 'Behavior' block — a strong structure for a dense tool. Slightly redundant: the pubmed_evidence_table contrast is stated twice (in the 'Unlike' clause and again in the 'Do not use' clause), and the parameters section reads as one long run-on paragraph.

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 17-parameter, zero-required-parameter, no-output-schema tool, the description covers purpose, alternatives, defaults, billing mechanics, latency, timeout recovery, and a full field inventory of returned items. Nothing an agent needs in order to call it correctly or budget for it appears to be missing.

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 coverage is 100%, so the baseline is 3; the description goes further by explaining that countries/states/city keep trials with at least one matching site and surface matchingSiteCount, and that requireContact filters uncontactable trials before billing. The run_max_items vs maxResults billing interaction is a genuinely non-obvious semantic that the schema text only hints at, though a couple of filter params (keywords, intervention) get no extra treatment.

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?

Opens with a specific verb and resource ('Find clinical trials on the official ClinicalTrials.gov API') and enumerates the filter axes plus returned entities (sponsors, sites, contacts, investigators). It explicitly distinguishes itself from two named alternatives (pubmed_evidence_table for articles, npi_provider_lists for providers), so an agent can classify it without reading the schema.

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?

Gives concrete when-to-use cases (recruiting trials near a location, sponsor/site pipelines, investigator and site-contact leads for CROs, suppliers, patient referral) and explicit when-not-to-use routing to pubmed_evidence_table and grants_finder. It also adds per-parameter usage guidance such as 'add COMPLETED etc. for history' and 'updatedWithinDays suits weekly schedules'.

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