Skip to main content
Glama

Claimora

by si.claimora
OverviewDiscussionsAdmin

search_smart

Find claims from a natural-language question. This build matches text only.

Use this when the input is a question instead of keywords.
Example: search_smart(natural_language="How do transformers handle long context?", domain="ai-ml", limit=5).
Example: search_smart(natural_language="What limits healthspan?", domain="longevity", limit=5).

Input Schema

NameRequiredDescriptionDefault
limitNoPage size. Example: 5.
domainNoRestrict results to one domain. Example: ai-ml.
offsetNoNumber of hits to skip. Example: 0.
natural_languageYesA question or description of the claims you want. Example: How do transformers handle long context?

Output Schema

NameRequiredDescriptionDefault
pageYes
claimsYes
strategyNolexical

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / domain / description
      Previous value: -"Restrict results to one domain."New value: +"Restrict results to one domain. Example: ai-ml."
    • addedInput schema / properties / domain / examples
      Added value: +[
+  "ai-ml"
+]
    • addedInput schema / properties / limit / description
      Added value: +"Page size. Example: 5."
    • addedInput schema / properties / limit / examples
      Added value: +[
+  5
+]
    • changedInput schema / properties / natural_language / description
      Previous value: -"A question or description of the claims you want."New value: +"A question or description of the claims you want. Example: How do transformers handle long context?"
    • addedInput schema / properties / natural_language / examples
      Added value: +[
+  "How do transformers handle long context?"
+]
    • addedInput schema / properties / offset / description
      Added value: +"Number of hits to skip. Example: 0."
    • addedInput schema / properties / offset / examples
      Added value: +[
+  0
+]
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden. It usefully discloses a real limitation ('This build matches text only'), which tells an agent there is no semantic matching, but says nothing about auth, rate limits, or how paging interacts across calls (beyond offset in the schema) — and an output schema covers return values.

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?

Front-loaded with purpose then the selection rule, with no filler. The two examples are near-duplicates in shape (only domain differs), so one would have sufficed.

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?

An output schema exists and parameters are fully documented, so the description only needed to cover routing and behavior — which it mostly does, including the text-only limitation. Slightly incomplete on pagination guidance across the offset/limit pair.

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 100% with per-parameter examples already present, so the baseline is 3. The two worked examples show domain and limit combined in a real call, adding modest usage context but no new semantics for offset or null-domain behavior.

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?

States a specific verb and resource ('Find claims') and scopes the tool to natural-language questions rather than keywords. It implies the keyword-mode sibling without naming query_claims, so differentiation is inferable rather than explicit.

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?

'Use this when the input is a question instead of keywords' gives a concrete selection rule against the sibling path. No explicit exclusions or named alternatives, but the condition is clear enough to route correctly.

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

All Claimora toolsInspect
Try in Browser
Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources