Skip to main content
Glama

add_screenshot

Append a screenshot (with an optional note) to a review created by create_review. The image is stored durably in Cobalt — this is the way to persist screenshots that would otherwise be lost when they only pass through a browser tool. Call once per screen as you go. Input is image_url: POST the image to https://cobaltcapture.com/api/upload (multipart field file, no auth, returns {url, key}) and pass back the url. If a browser-automation script took the screenshot, do that POST inside the same script (Python requests.post(...), or Playwright's request context) rather than shelling out to curl afterwards — same result, one less permission prompt. The image base64 parameter exists for small images only: tool-call arguments are model-generated text, so a real screenshot means emitting tens of thousands of base64 tokens perfectly, and an image you received as an image cannot be transcribed at all.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
imageNoFor SMALL images only (< ~100 KB) that you already hold as base64 text: a base64-encoded PNG/JPEG/WebP (data: URL prefix accepted). Not the path for screenshots — emitting one as tool-call text is slow and error-prone, and an image you received as an image cannot be transcribed. Upload it and pass image_url instead.
titleNoOptional short caption for the screenshot.
reviewYesThe review slug or URL from create_review.
commentNoOptional note describing what this screen shows or what's wrong with it.
image_urlNoThe image URL returned by Cobalt's own upload: POST the file as multipart field `file` to https://cobaltcapture.com/api/upload (returns {url, key}) — ideally from inside the script that captured it — or use the browser hook window.cobaltGrab(). Must be on Cobalt's own image host; external URLs are refused.
source_urlNoOptional URL of the page the screenshot was taken on.
claim_tokenYesThe claim_token from create_review (authorizes the write).

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing durable storage in Cobalt, the requirement that image_url must be on Cobalt's own host (external URLs refused), the no-auth upload endpoint, the claim_token authorization, and the base64 emission/transcription pitfalls. These are concrete behavioral details an agent needs before calling.

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 longer than typical but every section earns its place: purpose, upload workflow, browser-script guidance, and the base64 warning. It is front-loaded with the core action and then provides operational detail. Slightly dense, but not wasteful.

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?

For a 7-parameter tool with no output schema, the description covers the critical operational context: how to obtain a valid image_url, the alternative image path with limits, the claim_token authorization, and the per-screen call cadence. It does not describe the response or error behavior, but the essential calling context is present.

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 the baseline is 3, but the description adds meaningful semantics: it specifies the exact upload endpoint, multipart field, response format, the constraint that external URLs are refused, and when image should be used instead of image_url. This meaningfully enhances the agent's understanding beyond the schema.

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 opening sentence states a specific verb and resource: 'Append a screenshot (with an optional note) to a review created by create_review.' This clearly distinguishes the tool from siblings like add_note and get_review, and the instruction 'Call once per screen as you go' reinforces its exact purpose.

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?

The description gives clear when-to-use guidance: persist screenshots that would otherwise be lost, call once per screen, and use the image_url path for real screenshots. It does not explicitly compare against sibling alternatives like add_note, but it provides strong contextual usage rules and a clear workflow.

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

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: reviews (create/get/update/email/add content), inboxes (create/check), and playbooks (get). No two tools overlap in purpose, and descriptions reinforce the boundaries.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (add_, check_, create_, email_, get_, update_). The verbs clearly indicate the operation and the nouns indicate the resource, making the API predictable.

Tool Count5/5

Nine tools is well-scoped for the server's purpose: covering review lifecycle, inbox support, and playbook retrieval without redundancy. Each tool earns its place in the QA/capture workflow.

Completeness4/5

The tool surface covers the full review lifecycle (create, append, retrieve, update, email) plus supportive inbox and playbook operations. Minor gaps like no explicit delete or list operations exist, but auto-expiry and share-link retrieval mitigate them.

Resources