Skip to main content
Glama

create_reference

Create an upload slot for a reference image. Returns an upload URL and a ref_ token: upload the image file with one shell command (curl -T ''), then pass the ref_ token to the reference-image parameter you are filling - every parameter that takes reference images names this tool in its description. This is the ONLY way to supply reference images, and those parameters accept ref_ tokens and nothing else. Image data never goes inside a tool call: a call is JSON, so an embedded image would have to be base64 text that you, the caller, must emit character by character - slow, error-prone, and enough to exhaust your context window. The upload moves the bytes out-of-band instead: a plain HTTP PUT of the raw file, so any HTTP client works; if your environment has no way to send one, install curl. And when the image you want is from one of your OWN recent Logospell generations, skip the upload entirely: pass sourceGeneration and sourceImage and the server copies it directly - the shortcut for extending an existing set in its own style. Accepts PNG, JPEG, or WebP, each at most 500KB, each side between 64px and 768px - resize before uploading if needed; larger reference images do not improve results. A reference is private to your API key and can be used in any number of later calls; its expiry window restarts each time you use or re-upload it, so uploading a few references once can serve a whole session of work. Costs no credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceImageNoOptional, with sourceGeneration: the delivered image filename to use as the reference, exactly as listed by list_recent_generations or the generation's manifest (e.g. "a_lotus_cradling_a_glowing_pearl.png"). An image larger than the reference limits is downscaled to fit automatically.
sourceGenerationNoOptional, with sourceImage: fill this reference from one of your own recent generations instead of uploading a file. Pass the generation id - the random segment of its download URL (.../download/<id>/images.zip), also returned by list_recent_generations. The image is copied server-side; nothing is uploaded.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
refYes
expiresAtYes
uploadURLYes

TDQS

A4.9/5.0
Behavior5/5

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

The description discloses extensive behavioral details beyond annotations: the upload URL and ref_ token workflow, the out-of-band HTTP PUT mechanism, the per-key privacy and rolling expiry window, cost implications, and the explicit rationale against embedding base64 in JSON. This is far more transparent than the minimal annotations.

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?

The description is a single dense paragraph but well-structured, moving from purpose to mechanics to constraints. It is slightly longer than necessary—some rationale (e.g., base64 context pain) could be trimmed—but every sentence contributes to operational understanding, so it remains efficient.

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?

The description covers all essential context: return values, prerequisites (image format/size limits), the upload mechanism, the alternative shortcut, privacy/expiry behavior, and cost. Given the output schema exists and the description explains what is returned, it is fully complete for an agent to invoke correctly.

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

Parameters5/5

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

While the schema covers parameter descriptions at 100%, the description adds meaning by explaining how sourceGeneration and sourceImage work together, that sourceImage is downscaled to fit, and that these parameters are the shortcut path that skips uploading. It also clarifies the token-based interaction with other tools' parameters.

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 opens with a specific verb and resource: 'Create an upload slot for a reference image.' It clearly distinguishes itself from siblings by stating 'This is the ONLY way to supply reference images,' making it unmistakable which tool to invoke for this purpose.

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?

The description provides explicit guidance on when to use the tool versus alternatives: it is the only way to supply reference images, and when using one's own recent generations, the description directs to skip the upload and use sourceGeneration/sourceImage instead. It also notes the edge case of needing to resize images before uploading.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool targets a clearly distinct operation: three generation tools are explicitly differentiated by output type (single illustration vs. solid-color set vs. transparent set), while reference upload, editing, export, credit checking, and listing are all unambiguous. Cross-references between tools further eliminate any boundary confusion.

Naming Consistency5/5

All eight tools follow the same snake_case verb_noun pattern: check_, create_, edit_, export_, generate_, list_. The three generate_* tools share a common prefix with distinct objects, making the naming predictable and scannable.

Tool Count5/5

Eight tools is well-scoped for a logo/icon generation service: three generation variants, one editing tool, one export tool, one reference upload mechanism, plus account and history utilities. Each tool earns its place without redundancy or bloat.

Completeness5/5

The tool surface covers the full creative lifecycle: reference preparation (create_reference), generation (three variants), post-processing (edit_image_set), delivery conversion (export_icons), and session management (list_recent_generations, check_credits). Deletion is unnecessary because references and downloads expire naturally, so there are no dead ends.

Resources