getdeck

Check slots

check_slots

Read-onlyIdempotent

Validate slot text against a layout before rendering. Nothing is rendered and no CSS is returned, so it is cheap: run it on every slide you wrote, fix what it reports, then call render_slide. Input: layout_id and slots (slot id to text), the same as render_slide. Returns { layout_id, ok, error_count, warning_count, issues[] }. Each issue has slot, code (unknown_slot, missing_required, empty_required, too_long, not_filled, blanked), severity ("error" must be fixed, "warning" is a quality note) and a one-line fix. ok is true when there are no errors.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "layout_id": "<layout_id>",
      "slots": "<slots>"
    },
    "name": "check_slots"
  }
}

Input Schema

Name	Required	Description	Default
`slots`	Yes	Slot id to text, e.g. {"title": "Revenue grew 40%"}. Ids and limits come from get_layout / list_layouts slots[]. Plain text only: it is HTML-escaped, and a newline becomes a line break. Pass "" to leave an optional slot blank; a slot you omit keeps the layout's sample copy.
`layout_id`	Yes	Layout id from list_layouts or suggest_deck.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026
- addedInput schema / properties / layout_id / description
```
Added value: +"Layout id from list_layouts or suggest_deck."
```
AddedNov 5, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description still adds real value: it discloses that nothing is rendered and no CSS is returned, that failures are reported rather than thrown, and that severity distinguishes 'must be fixed' errors from quality warnings. That severity contract is behavior an agent cannot get from any structured field here.

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

Conciseness5/5

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

Front-loaded with the purpose and the cost/ordering rationale, then inputs, then return shape, then issue semantics — each sentence carries distinct information. The code enumeration is compact and directly actionable rather than padding.

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?

There is no output schema, so the description carries the return contract itself and does so precisely ({ layout_id, ok, error_count, warning_count, issues[] } plus per-issue fields and the meaning of ok). For a two-parameter validator with a nested slots object, nothing an agent needs to call and interpret it is missing.

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% and the slots property is richly documented (escaping, newline handling, empty string vs omitted), so the baseline is 3. The description earns one above baseline by stating the input is 'the same as render_slide', which gives the agent a transferable mental model, plus it names the two issue-relevant input fields explicitly.

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 and resource — 'Validate slot text against a layout' — and immediately frames it as a pre-render step, which cleanly separates it from render_slide and from the object mutation siblings. An agent knows exactly what this does without opening the schema.

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?

Explicit when-to-use: 'run it on every slide you wrote, fix what it reports, then call render_slide.' It names the ordering constraint relative to a specific sibling and even states the cost rationale ('it is cheap') that justifies the habit. No inference required.

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

All getdeck tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?