Skip to main content
Glama

image-processing

by ai.pictomancer

optimize_for_vision

Resize an image for a vision model

Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting tokens, so this alone saves bytes and upload latency rather than tokens. Pass max_tokens to trade resolution for tokens: that lever is continuous on Claude, unavailable on OpenAI (cost follows the aspect ratio alone), and on Gemini reaches only a flat 258. An image already within budget is returned untouched and free (X-Pig-Billed: 0).

Responses:

200: Processed image binary (Success Response) Content-Type: application/json Content-Type: image/jpeg

Example Response:

"string"

Content-Type: image/png

Example Response:

"string"

Content-Type: image/webp

Example Response:

"string"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoQuality (1-100). Maps to libvips Q parameter.
formatNoOutput format: jpeg, png, webp, tiff, gif, or avif. If omitted, the original format is preserved.
sourceYesImage source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).
deliveryNo
max_tokensNoOptional cap on what the image may cost the target model. Without it the image is resized to the model's own ceiling, which saves bytes and upload latency but no tokens, because every provider already downscales oversized input before counting. Set a budget to trade resolution for tokens. The response reports the cost actually achieved: on OpenAI it cannot be lowered by resizing at all, and on Gemini only down to a flat 258.
target_modelYesVision model the image is being prepared for, e.g. claude-opus-5, gpt-4o, gemini-2.5-pro. Unknown ids are rejected rather than guessed: the wrong limits would silently resize to the wrong size.

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that resizing alone saves bytes/latency but not tokens, that max_tokens behaves differently across Claude/OpenAI/Gemini, and that in-budget images are returned untouched and free (X-Pig-Billed: 0). It does not discuss rate limits or auth, but those are less central here.

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 main paragraph is front-loaded and dense with meaningful info about provider-specific behavior and token economics. The Responses section is slightly redundant with repeated Content-Type headers and 'string' placeholders, but it does provide return-type hints in the absence of an output schema.

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?

Given no output schema, the description explains the outcome (resized image, token cost report, free/billed header) and includes response examples. The schema covers the remaining parameter semantics well. Minor gap: it does not detail error cases beyond the schema's note on unknown model IDs.

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 83% and parameter docs are already detailed (e.g., max_tokens and target_model). The description reinforces max_tokens behavior but adds little beyond the schema's own parameter descriptions, so the baseline of 3 is appropriate.

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 resizes an image for a vision model and reports its token cost before and after. This specific verb+resource+scope distinguishes it from sibling tools like resize_image or compress_image, which do not include model-specific token reporting.

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 provides clear context: use this when preparing an image for a vision model, and explains when to pass max_tokens to trade resolution for tokens. However, it does not explicitly name alternatives or state when not to use this tool versus resize_image or compress_image, so it lacks explicit exclusions.

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

All image-processing toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Most tools are distinct, but compress_image, convert_image, and optimize_generated_image overlap heavily: all re-encode images with format and quality options. The descriptions clarify intent, yet an agent could still struggle to pick between compressing, converting, and optimizing in some cases.

Naming Consistency4/5

The set mostly follows a verb_noun pattern (analyze_image, compress_image, crop_image, resize_image). Minor deviations include image_pipeline, which is a noun phrase, and optimize_for_vision/optimize_generated_image, which use longer prepositional forms, but the overall pattern is predictable.

Tool Count5/5

Ten tools is well within the ideal range for an image-processing server. Each tool serves a meaningful purpose, and the count feels neither bloated nor thin.

Completeness4/5

Core image operations are well covered: analyze, resize, crop, convert, compress, pipeline, plus cost/format introspection. Minor gaps like rotate/flip or explicit metadata editing are absent, but agents can accomplish most workflows with the existing surface.

Resources