Skip to main content
Glama
smeet666

mcp-stashbox

Search scenes

search_scenes
Read-onlyIdempotent

Search scenes across multiple stash-box catalogues with full-text or faceted queries. Each catalogue reports its own count and status (failed, not asked, or no matches).

Instructions

Ask every configured catalogue for scenes. The two paths are exclusive: giving 'query' runs the full-text search and every typed argument is reported as not received, while omitting it runs the faceted query on the typed arguments. A catalogue offering no full-text search is named as absent from a 'query' search, and dropping 'query' for 'title' reaches it. Counts are per catalogue and are never added, and a catalogue that failed, one never asked and one that found nothing are three different states an answer names.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeNoThe studio's own reference for the scene.
pageNo
sortNo
limitNo
queryNoFree text matched against a scene's own fields.
titleNo
date_toNoLatest release date, as YYYY-MM-DD.
sourcesNo
tag_idsNo
date_fromNoEarliest release date, as YYYY-MM-DD.
directionNo
studio_idsNo
performer_idsNoNamespaced performer identifiers.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
notesYes
queryYes
windowNoThe window this answer covers, per catalogue. An emptiness here is an emptiness inside that window.
resultsYes
orderingYesHow the order was built. The catalogues publish no score in common, so rows interleave and nothing is ranked across them.
per_sourceYes
result_countYesRows returned here. Counts are never added across catalogues.
Behavior5/5

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

The description discloses non-obvious behaviors: exclusive query paths, per-catalogue counts that are never added, and three distinct result states (failed, never asked, found nothing). It also notes behavior when a catalogue lacks full-text search, adding value beyond the readOnly/idempotent annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with a clear primary statement, but the second sentence is dense and uses confusing phrasings like 'reported as not received' and 'dropping query for title,' making it harder to parse than necessary.

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?

The description captures the most intricate behaviors (exclusive modes, catalogue states) and the output schema exists, so return format is covered. However, it leaves some ambiguities around parameter combinations and does not mention pagination or aggregation across catalogues.

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?

With only 38% schema coverage, the description compensates partially by explaining the query vs faceted mode interaction and the role of 'title' in reaching catalogues without full-text search. However, it does not clarify the remaining parameters (sort, page, sources, etc.) beyond what the schema already states.

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 clearly states the tool queries every configured catalogue for scenes, using a specific verb and resource. This distinguishes it from siblings like search_performers (performers) and get_scene (single scene).

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?

It explains the exclusive use of 'query' for full-text search versus faceted search with other parameters, and even gives a specific scenario for using 'title' to reach catalogues without full-text support. However, it does not explicitly contrast with sibling tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smeet666/mcp-stashbox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server