Tokenrip

Search artifacts

search

Read-onlyIdempotent

Search readable artifacts. Scoped to a workspace (workspaceId, or an artifactId in one), each result carries its best passages, and ranking blends keywords with meaning where the server has an embedding provider; pending counts chunks not yet searchable by meaning. Elsewhere, keyword ranking. Follow nextCursor as offset for remaining results; mode reports how the search ranked.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search"
  }
}

Input Schema

Name	Required	Description
`q`	No	The search text. Omit it to list by recency within the other filters.
`team`	No	Only artifacts shared with this team (slug or id). Not with workspaceId.
`type`	No	Only artifacts of this type.
`limit`	No	Results per page, 1 to 200 (with artifactId, passages of that one artifact).
`since`	No	Only what happened since: an ISO 8601 timestamp, or a number of days back (7 = the last week).
`offset`	No	Results to skip: the next page starts here.
`artifactId`	No	Search one artifact (its id or alias): its best passages, best first, up to limit. In a workspace, pass no scope or its own workspaceId.
`workspaceId`	No	Search one workspace, by its id or its slug (not with team): ranks by keywords, and by meaning too where the server has an embedding provider, and returns each result's best passages. A workspace you cannot read is refused before the query is embedded.

Output Schema

Name	Required	Description	Default
`mode`	Yes
`items`	Yes
`total`	Yes
`partial`	Yes
`pending`	No
`nextCursor`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / workspaceId / description

Previous value: -"Search one workspace, by its id or its slug (not with team): ranks by keywords and meaning together, and returns each result's best passages. A workspace you cannot read is refused before the query is embedded."New value: +"Search one workspace, by its id or its slug (not with team): ranks by keywords, and by meaning too where the server has an embedding provider, and returns each result's best passages. A workspace you cannot read is refused before the query is embedded."

Changed5 schema fields changedOct 24, 2026

changedInput schema / properties / workspaceId / description

Previous value: -"Search one workspace (not with team): ranks by keywords and meaning together, and returns each result's best passages. A workspace you cannot read is refused before the query is embedded."New value: +"Search one workspace, by its id or its slug (not with team): ranks by keywords and meaning together, and returns each result's best passages. A workspace you cannot read is refused before the query is embedded."

removedInput schema / properties / workspaceId / format
```
Removed value: -"uuid"
```
addedInput schema / properties / workspaceId / maxLength
```
Added value: +64
```
addedInput schema / properties / workspaceId / minLength
```
Added value: +1
```

removedInput schema / properties / workspaceId / pattern

Removed value: -"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"

First observedOct 23, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real behavior: hybrid keyword-plus-meaning ranking when an embedding provider exists, keyword-only otherwise, `pending` counting not-yet-embedded chunks, and nextCursor being an offset. It stops short of stating result ordering guarantees or rate limits, but the disclosed traits are substantive.

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 the core action, then scope, then ranking, then pagination — a sensible information order with no filler sentences. It is dense to the point of being semicolon-heavy, packing several distinct facts into each clause, which slightly hurts skimmability.

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?

With 8 fully documented params, annotations, and an output schema, the description covers the non-obvious pieces an agent needs (scope semantics, hybrid vs keyword ranking, cursor continuation). The remaining gap is guidance on when to prefer this over artifact_list/artifact_get for browsing vs searching.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description still earns credit by summarizing the cross-parameter scoping model (workspaceId vs artifactId-within-a-workspace) and tying ranking behavior to which scope is chosen. It does not add much on q/limit/since/offset beyond what schemas already state precisely.

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?

Opens with a specific verb+resource ("Search readable artifacts") and immediately states scoping (workspace, or one artifact) and ranking behavior. An agent can tell this is a retrieval tool distinct from artifact_get / artifact_list, but the description never names those siblings explicitly, leaving the boundary to inference.

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

Usage Guidelines3/5

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

Usage context is implied through the scoping sentences (workspace-wide vs single-artifact via artifactId, and "Elsewhere, keyword ranking"), but there is no explicit "use this instead of artifact_list when..." guidance and no statement of when not to use it. The agent must derive selection rules from the schema's own descriptions.

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

All Tokenrip tools Inspect

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.