ppsspp-dfx

Overview Schema Source Related Servers Discussions Admin

ppsspp_dump

Read-onlyIdempotent

Captures the currently bound GPU texture or CLUT palette as an image with metadata, aiding debugging of PPSSPP rendering.

Instructions

PURPOSE: Dump the currently-bound GPU texture OR CLUT palette as an image plus metadata.

USAGE: kind='texture' → the bound texture (level selects mipmap; PPSSPP captures the currently-bound texture — it does NOT support capture by VRAM address); kind='clut' → the bound palette (level must be 0).

BEHAVIOR: READ-ONLY. An empty capture raises CAPTURE_EMPTY — enter a scene that renders (texture) or uses the palette (clut) and retry.

RETURNS: structuredContent metadata (kind/level/file_path/size_bytes/format); the image itself arrives as an ImageContent block.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	Yes	What to capture from the CURRENTLY bound GPU state (no VRAM-address targeting): 'texture' = the bound texture (use level for mipmap); 'clut' = the bound CLUT palette.
`level`	No	Texture mipmap level (default 0). kind=texture only — a non-zero level with kind=clut is rejected.
`session_id`	Yes	Active session ID.

Output Schema

TableJSON Schema

Name	Required	Description
`level`	Yes	Texture mipmap level dumped.
`format`	Yes	Image format ('png' or 'jpeg').
`file_path`	Yes	Path where image was saved.
`size_bytes`	Yes	Decoded image size in bytes.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.6Oct 4, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds real behavior beyond that: a documented failure mode (CAPTURE_EMPTY) with a retry remedy, the constraint that capture is by currently-bound state only (no VRAM-address targeting), and the response shape. This is genuinely useful error/limitation disclosure.

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?

Labeled sections (PURPOSE/USAGE/BEHAVIOR/RETURNS) front-load the key information and every sentence carries weight. The only cost is some duplication of the schema's kind/level descriptions, which slightly dilutes conciseness.

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?

With an output schema present, the description needn't detail return values, and it still summarizes structuredContent fields and the ImageContent block. Between annotations, schema, and the error guidance, an agent has everything needed to invoke it correctly.

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%, so all three parameters are already documented, including the enum and the clut/level rejection rule. The description largely restates the same semantics (no VRAM-address targeting is the only marginal addition), so baseline 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+resource: dump the currently-bound GPU texture or CLUT palette as image plus metadata. It is clearly distinguishable from siblings like ppsspp_screenshot and ppsspp_gpu_record because it names GPU texture/CLUT capture as the scope.

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?

Gives explicit per-value guidance (kind='texture' uses level for mipmap; kind='clut' requires level=0) and tells the agent what to do when capture is empty. It does not, however, name an alternative tool for related needs (e.g., screenshot), so it stops short of full when/when-not routing.

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