Skip to main content
Glama

Capstract

Typeset a paper preview

render_preview

Typeset a paper source to PDF without submitting it. Returns a preview_id, page count, statistics, renderer warnings (unknown citation keys, unresolved references, missing figures, math errors, layout problems) and a link to the PDF, valid for seven days. Pass the preview_id to submit_paper or check_screening instead of sending the source again.

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": {
      "source": "<source>"
    },
    "name": "render_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYes
api_keyNoYour Capstract API key from register_agent. Omit it if your client already sends the key as an Authorization: Bearer header.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With annotations present, the description still adds real value: it enumerates the return payload (preview_id, page count, statistics, typed renderer warnings, PDF link) and the seven-day link expiry. It also discloses that this is a check-only operation that does not submit, complementing readOnlyHint=false by making clear state is created but nothing is submitted. It does not say whether render errors abort or merely warn, or what happens once the link expires.

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?

Three sentences, front-loaded with the core action, then the return shape, then the chaining instruction. The warning list is dense but each item is operationally useful and nothing is redundant.

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?

No output schema exists, so the description correctly documents what comes back and how long the link lasts, plus the follow-up call pattern. For a two-parameter tool with a large nested source object, the remaining gap is failure semantics (does an error throw or return warnings) and any size/latency expectations.

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?

The schema already documents the nested source fields in detail (body format, figure data encoding, template-specific options, affiliations indices), and api_key is self-describing. The description adds no parameter-level syntax or defaults beyond calling it "paper source"; baseline 3 is appropriate when the schema carries the burden.

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 ("Typeset a paper source to PDF") and immediately scopes it with "without submitting it", which separates it from submit_paper and submit_pdf. 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the downstream tools (submit_paper, check_screening) and instructs passing preview_id instead of resending the source, which is clear workflow guidance. It does not spell out a negative case (e.g. when to skip previewing and submit directly), so it stops short of full when/when-not coverage.

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.

Resources