WritersLogic verifiable AI agents

abandoned-compound-miner

Abandoned Compound & Uncommercialized Trial Miner — Finds shelved drug and biologic candidates worth a second look. Give a disease or target (mines ClinicalTrials.gov for terminated, withdrawn and suspended trials and for completed Phase 1/2 non-industry trials with no later industry Phase 2/3/4 trial), a compound you already have in mind (drug name or ChEMBL id), a trial (NCT id), or a desired material property (literature mode, no trials). Every

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "abandoned-compound-miner"
  }
}

Input Schema

Name	Required	Description
`nctId`	No	A ClinicalTrials.gov trial id (e.g. "NCT01257048"). The compound it tested is reviewed as with `compound`.
`compound`	No	A compound you already have in mind, as a drug name or ChEMBL id (e.g. "edaravone", "CHEMBL290916"). Returns whether it is an abandoned, safe-to-pursue candidate or why it was excluded (marketed, safety signal, active development). Replaces the condition search.
`maxCandidates`	No	Dossiers to produce (default 4, max 8). Model cost is at most one fast call per candidate.
`materialProperty`	No	Desired material property (e.g. "high ionic conductivity solid electrolyte"). Mines the literature indexes; no trials are involved.
`includeCompletedNoFollowUp`	No	Include completed Phase 1/2 non-industry trials with no later industry Phase 2/3/4 trial of the same intervention. Default true.
`biologicalTargetOrCondition`	No	Disease, condition or biological target (e.g. "amyotrophic lateral sclerosis", "BACE1"). Mines stopped and completed-without-follow-up clinical trials.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

B3.4/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does substantial work: it discloses the data sources (ClinicalTrials.gov, literature indexes), the inclusion criteria (terminated, withdrawn, suspended; completed Phase 1/2 non-industry with no later industry Phase 2/3/4), and the exclusion reasons (marketed, safety signal, active development). What it omits is cost/latency and output shape, though the schema partially covers model cost.

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

Conciseness2/5

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

The mode enumeration is front-loaded and useful, but the description terminates mid-sentence at 'Every ', which is a hard defect signalling lost content. The branding clause ('worth a second look') is expendable, and the agent is left with a visibly incomplete definition.

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

Completeness3/5

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

For a six-parameter tool with no annotations and no output schema, the description covers input modes and screening criteria reasonably well, but the truncation removes whatever came after 'Every ' — plausibly return format or caveats — and nothing describes what a produced 'dossier' contains beyond the schema's brief note.

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 description coverage is 100%, so the schema already explains every parameter including the mode-exclusivity note ('Replaces the condition search') and the default/max on maxCandidates. The description adds the mode-level framing but does not clarify that the four mode parameters are mutually exclusive alternatives, so it does not meaningfully exceed the schema baseline.

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

Purpose4/5

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

The description names a specific verb+resource (mines ClinicalTrials.gov and literature indexes for shelved drug/biologic candidates) and enumerates four distinct entry modes: disease/target, compound, NCT id, and material property. This is far more specific than the name alone, though the final sentence is truncated and the tool's scope boundary against siblings like future-work-miner is never stated.

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

Usage Guidelines3/5

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

The opening sentence 'Give a disease or target..., a compound..., a trial..., or a desired material property' effectively tells the agent which input selects which mode, and material property is explicitly flagged as 'literature mode, no trials.' However there is no guidance on when NOT to use this tool versus alternatives, and the sentence is cut off mid-thought, leaving the selection rules incomplete.

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

All WritersLogic verifiable AI agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?