nullary

search_safety_failures

Read-onlyIdempotent

Clinical/preclinical safety failures across modalities.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tier`	No	Confidence tier. 'curated' (default) returns the credible layer; 'all' also includes high-volume screening-grade rows (PubChem HTS inactives, CRISPR non-essential tails).	curated
`limit`	No	Maximum number of findings to return (1–100, default 25).
`offset`	No	Number of findings to skip before this page, for pagination (default 0).
`target`	No	UniProt accession or gene symbol
`outcome`	No	outcome filter (inactive, failed_safety, terminated, …)
`compound`	No	compound name, ChEMBL ID, or InChIKey

Output Schema

TableJSON Schema

Name	Required	Description
`findings`	No	Matching negative findings (same shape as the REST /findings endpoint).
`has_more`	No	True when more results exist beyond this page.
`coverage_note`	No	Honest coverage caveat for thin Phase-1 modalities (present only when relevant).
`query_metadata`	Yes	Echo of the resolved query — tool, limit, offset, and any applied presets.
`returned_count`	No	Findings returned in this page.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed3 schema fields changedMay 25, 2026

addedInput schema / properties / limit / description

Added value: +"Maximum number of findings to return (1–100, default 25)."

addedInput schema / properties / offset / description

Added value: +"Number of findings to skip before this page, for pagination (default 0)."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "coverage_note": {
+      "description": "Honest coverage caveat for thin Phase-1 modalities (present only when relevant).",
+      "type": "string"
+    },
+    "findings": {
+      "description": "Matching negative findings (same shape as the REST /findings endpoint).",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "has_more": {
+      "description": "True when more results exist beyond this page.",
+      "type": "boolean"
+    },
+    "query_metadata": {
+      "description": "Echo of the resolved query — tool, limit, offset, and any applied presets.",
+      "type": "object"
+    },
+    "returned_count": {
+      "description": "Findings returned in this page.",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "query_metadata"
+  ],
+  "type": "object"
+}

First observedMay 25, 2026

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds scope context ('clinical/preclinical', 'across modalities') which annotations do not provide. However, it does not disclose any behavioral details such as default filtering behavior (e.g., tier='curated'), pagination, or the fact that it returns findings. The presence of openWorldHint is not leveraged in the description.

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

Conciseness4/5

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

The description is a single compact phrase with zero filler words, making it highly concise and front-loaded with the core domain ('safety failures'). However, its brevity borders on under-specification for a tool with six parameters and many siblings; a slightly longer description could add value without sacrificing conciseness.

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

Completeness2/5

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

Despite the presence of an output schema and detailed parameter descriptions, the tool description is too skeletal for the complexity of the tool and its crowded sibling landscape. It fails to explain how this search differs from similarly named tools like search_admet_failures_all_modalities or search_failed_antibodies, and it does not mention the tier concept (curated vs all) or the types of outcomes included. The agent lacks enough context to confidently select this tool for a given query.

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?

The input schema provides 100% coverage for all 6 parameters, each with descriptive text (tier, limit, offset, target, outcome, compound). The tool description adds no parameter-specific information, but the schema descriptions are sufficient. Baseline 3 is appropriate since the schema carries the full burden and the description does not contradict or add meaningful parameter context.

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 'Clinical/preclinical safety failures across modalities' clearly identifies the resource (safety failures) and scope (clinical/preclinical, across modalities), distinguishing it from more specific sibling tools like search_admet_failures or search_failed_antibodies. However, it lacks an explicit verb like 'search' or 'list', relying on the tool name to convey the action. This makes it slightly less direct than the ideal 'verb + resource + scope' formulation.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus its many siblings such as search_admet_failures_all_modalities, search_failed_antibodies, or search_developability_failures. The description does not mention exclusions, prerequisites, or specific use cases. The agent is left to infer the intended usage from the name alone.

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

All nullary tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?