Santismm Knowledge — Harness Engineering, Agentic AI & Governance

Search Harness Engineering & Agentic AI

search

Read-onlyIdempotent

Ranked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook). Matches every language and ignores accents, so query in the user's own words. Each hit carries a relevance score and the fields it matched; follow up with the matching get_* tool for full detail. Use this before any get_* tool whenever you have a question rather than an identifier.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max results (default 20).
`query`	Yes	Keyword or phrase to search for in any supported language.
`locale`	No	Language of the returned body. Default: en.
`domains`	No	Restrict to these domains. Omit to search everything, including the handbook.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`count`	Yes
`query`	Yes
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026
- addedOutput schema / properties / results / items / properties / how_to_cite
```
Added value: +{
+  "description": "The citation, already formed — use it verbatim.",
+  "type": "string"
+}
```
First observedSep 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is lower. The description still adds real context beyond them: cross-language matching, accent-insensitivity, that each hit carries a relevance score and matched fields, and the recommended follow-up with get_*. It stops short of stating result caps or ranking model details.

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?

Three tight sentences, front-loaded with the core scope, then behavior, then the routing instruction. Every sentence carries distinct information with no filler.

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, so return values needn't be described, and the description still usefully previews the hit shape and the follow-up path. It is nearly complete for a search tool; the missing piece is any differentiation from the sibling search family, which the agent needs to disambiguate.

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 documents query, limit, locale and domains with defaults and bounds. The description adds only generic guidance ('query in the user's own words', 'matches every language') rather than new syntax or format detail, so the baseline 3 is appropriate.

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 ('Ranked keyword search across the whole corpus') and enumerates the covered domains, so the agent knows exactly what is searched. However, it does not distinguish itself from the sibling 'search_all', which the phrase 'across the whole corpus' makes it sound identical to, leaving real ambiguity about which search entry point to pick.

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?

Explicitly routes the agent: 'Use this before any get_* tool whenever you have a question rather than an identifier.' That is a clear when-to-use vs when-not rule against the get_* family. It gives no guidance against the other search siblings (search_all, search_articles), which is the more likely confusion.

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

All Santismm Knowledge — Harness Engineering, Agentic AI & Governance tools Inspect

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.