Skip to main content
Glama

Clinicaltables

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Procedures

procedures
Read-onlyIdempotent

"What is the procedure called [X]" / "medical procedure name lookup" / "patient-friendly name for [surgery]" — search clinical procedure names (NLM curated, ~7k entries). Returns short names like "Appendectomy", "Knee replacement". Patient-facing language; use for forms or intake screens. This vocabulary is SMALL and curated, so common terms can legitimately miss ("colonoscopy" and "MRI" both return 0, verified 2026-09-16) — a no_match here means "not in this list", not "no such procedure". For billing codes use icd10cm or a CPT source instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dfNoComma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name.
efNoComma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov.
countNoMaximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing.
termsYesSearch query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: "appendectomy".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "count": 3,
+    "terms": "appendectomy"
+  }
+]
    • changedInput schema / properties / terms / description
      Previous value: -"Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: \"colonoscopy\"."New value: +"Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: \"appendectomy\"."
  2. Changed7 schema fields changed
    • addedInput schema / properties / count / default
      Added value: +7
    • addedInput schema / properties / count / description
      Added value: +"Maximum matches to return. Default 7, max 500. Use 1–3 for typeahead UX, 20–50 for browsing."
    • addedInput schema / properties / count / maximum
      Added value: +500
    • addedInput schema / properties / count / minimum
      Added value: +1
    • addedInput schema / properties / df / description
      Added value: +"Comma-separated display fields to use in the `displays` array. Default varies per table; usually the canonical name."
    • addedInput schema / properties / ef / description
      Added value: +"Comma-separated extra fields to include per match. Field names vary per table; check NLM docs at clinicaltables.nlm.nih.gov."
    • addedInput schema / properties / terms / description
      Added value: +"Search query — prefix/contains match against canonical names. Whitespace-split into AND tokens. Example: \"colonoscopy\"."
  3. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/openWorld annotations, the description discloses the no-match semantics ('no_match here means "not in this list", not "no such procedure"') and return style (short patient-friendly names). It even provides a verified date for the known misses, which is useful calibration for an agent. No contradiction with annotations.

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?

The description is compact yet dense: query phrases, resource scope, return examples, usage context, a calibrated limitation, and a routing instruction all appear without filler. Information is front-loaded with the purpose, followed by caveats.

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

Completeness5/5

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

For a tool with no output schema and four parameters, the description covers the essential behavior, expected returns, edge cases, and fallback routes. The absence of an output schema is mitigated by concrete return examples, and the annotations cover safety. Nothing critical is missing.

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 baseline of 3 applies. The description adds little param-specific detail beyond the schema: it reinforces 'appendectomy' as an example and frames terms as patient-facing, but the schema already covers prefix/contains matching, counts, and display fields. This is acceptable because the schema carries the load.

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?

The description opens with concrete query patterns and states the exact resource: NLM-curated clinical procedure names (~7k entries). It distinguishes itself from sibling vocabularies by explicitly saying billing codes belong in icd10cm or a CPT source, and the examples ('Appendectomy', 'Knee replacement') make the domain unambiguous.

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

Usage Guidelines5/5

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

It gives explicit when-to-use context ('use for forms or intake screens'), warns about a common failure mode (small curated vocabulary, 'colonoscopy' and 'MRI' return 0), and tells agents when not to use it ('For billing codes use icd10cm or a CPT source instead'). These exclusions and alternatives are concrete.

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

All Clinicaltables toolsInspect
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