Twelfth

Search docs

search_docs

Read-onlyIdempotent

Search Twelfth's product documentation for how a page, control or setting works, returning matching sections with links. Use it before saying Twelfth cannot do something. An empty result means the docs do not describe it, not that the product lacks it. For documents the workspace shared use read_document.

Input Schema

Name	Required	Description	Default
`limit`	No	Maximum sections to return (1 to 10).
`query`	Yes	The user's question in their own words. Plain language beats product jargon; the corpus is written the way a customer would ask.

Output Schema

Name	Required	Description
`note`	No	Present when nothing matched.
`query`	Yes
`sections`	Yes
`truncated`	Yes
`returned_rows`	Yes
`total_matching_rows`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

addedOutput schema / properties / sections / items / properties / slug

Added value: +{
+  "description": "The page's slug; fetch reads the whole page as docs:<slug>.",
+  "type": "string"
+}

Changed1 schema field changedOct 4, 2026

changedInput schema / properties / limit / description

Previous value: -"Maximum sections to return (1–10)."New value: +"Maximum sections to return (1 to 10)."

First observedOct 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: results include links, and an empty result signals corpus coverage rather than product capability. It stops short of describing ranking or relevance behavior, which keeps it from a 5.

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?

Four short sentences, each carrying distinct information: what it does, when to call it, how to interpret empty results, and which sibling to use instead. Nothing is redundant or padded.

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?

An output schema exists, so return-value detail is not required in the description, and annotations cover the safety profile. Given that, the description delivers everything an agent needs: purpose, trigger condition, result interpretation, and sibling routing.

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% and both parameters are documented in the schema, including the plain-language framing of query and the 1-10 bound on limit. The description adds no parameter-level detail beyond what the schema already supplies, so the baseline of 3 applies.

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?

States a specific verb (search), a specific resource (Twelfth's product documentation), the scope (how a page, control or setting works) and the return shape (matching sections with links). It also names the sibling it is not, read_document, so an agent can route correctly without opening either schema.

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?

Gives explicit when-to-use guidance ("Use it before saying Twelfth cannot do something") and an explicit alternative with its selecting condition ("For documents the workspace shared use read_document"). It even pre-empts misreading of negative results, which is unusually actionable.

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

All Twelfth tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.