Skip to main content
Glama

Clareo Health clinical trials

Find recently updated trials

get_recent_trial_changes
Read-onlyIdempotent

Find public clinical trials the registry updated on or after a date, for a condition (query) or to check one trial (nctId). This uses the registry's last-update date only: it tells you a record changed, not what changed, so send a person to the trial page for the details. Give either query or nctId, plus since as YYYY-MM-DD. Paged like search_clinical_trials. Send conditions and places only, never a person's name, diagnosis history, medications or other health details. Not medical advice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since": "<since>"
    },
    "name": "get_recent_trial_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
limitNo
nctIdNoOne trial to check. Use this or query.
queryNoCondition, treatment or sponsor. Use this or nctId.
sinceYesDate as YYYY-MM-DD; trials updated on or after it are kept.

Output Schema

NameRequiredDescriptionDefault
pageYes
basisYesWhat "changed" means here.
sinceYes
totalYes
hasMoreYes
resultsYes
nextPageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description still adds genuinely new behavior: the results reflect the last-update date only, not what changed, and results are paged. It also discloses a privacy constraint on inputs, which is context no annotation carries. It stops short of stating rate limits or result-cap behavior beyond the limit maximum.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the verb and scope, then the important caveat about what the date means, then the invocation rule, then the privacy/disclaimer line. Each sentence carries distinct information with no restatement of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values needn't be described, and the description covers mode selection, date semantics, paging and input privacy. The only gap is that pagination behavior is delegated by reference to a sibling rather than described, which slightly weakens completeness for an agent that hasn't inspected that sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, and the schema already documents nctId, query and since including formats and the either/or note. The description reinforces the query/nctId exclusivity and the date format but adds no new meaning for page/limit except pointing to 'paged like search_clinical_trials'. Useful reinforcement, but largely duplicative of structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('find public clinical trials the registry updated on or after a date') and immediately narrows the scope to the registry's last-update date, which separates it from a general keyword search. It also names its two operating modes (condition query vs. single nctId), so an agent can tell what kind of lookup this is without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete invocation guidance ('Give either query or nctId, plus since as YYYY-MM-DD') and an explicit downstream alternative for the details ('send a person to the trial page'), which is real routing advice. It does not explicitly contrast itself with search_clinical_trials or get_clinical_trial, so the when-not-to-use-this case is left implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources