Graph Paper

Evaluate steps

evaluate_steps

Read-only

Needs sign-in: Evaluate a sequence of LaTeX statements in order, in one shared scratch scope (over the definitions of the document named by documentId, if any), then discard the scope. A definition (a := 5, f(x) := x^2) is visible to later statements of the same call; nothing persists after the call and no document is changed. Use it for a multi-step calculation, or to verify candidate solutions (bind x := 2, then evaluate x^2 = 4). Evaluation stops at the first failing statement (stoppedAt is its 0-based index). Previous answers (%) are not available; name intermediates with :=.

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": {
      "statements": "<statements>"
    },
    "name": "evaluate_steps"
  }
}

Input Schema

Name	Required	Description	Default
`documentId`	No	The id of a document (from list_documents or search_documents). With it, the expression sees that document's definitions; without it, an empty scope.
`statements`	Yes	LaTeX statements evaluated in order in one shared, discarded-at-return scope. Definitions bind for later statements in this call only.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 24, 2026

TDQS

A4.5/5.0

Behavior5/5

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

It adds a lot beyond readOnlyHint/openWorldHint=false: a sign-in requirement, no persistence and no document mutation, fail-fast semantics with stoppedAt reported as a 0-based index, and the unavailability of prior-question references. These are exactly the behaviors an agent needs before chaining statements in a throwaway scope.

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 core scope behavior is front-loaded, and every sentence carries information about scope, persistence, fail-fast, or the workaround for named intermediates. There is mild redundancy between 'discard the scope' and 'nothing persists after the call', and the 'Needs sign-in:' prefix is appended awkwardly.

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 read-only evaluator with no output schema, the description covers scope, ordering, failure handling, and prerequisites well enough to call it correctly. What it does not describe is the shape of a successful result (how computed values per statement come back), which the agent must discover empirically.

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 baseline is 3, but the description adds real meaning: documentId controls which document's definitions seed the scope (versus an empty scope), and statement definitions bind only for later statements in the same call. It also documents result semantics (stoppedAt) that the schema cannot express.

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 states a specific verb (evaluate) and resource (an ordered sequence of LaTeX statements) together with the scope model: one shared scratch scope, discarded at return. The shared-scope semantics and the multi-step framing make it clearly distinct from its sibling evaluate_math.

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 explicitly says when to use it: 'for a multi-step calculation, or to verify candidate solutions (bind x := 2, then evaluate x^2 = 4)', and it rules out one tempting pattern by noting previous answers (\%) are not available. However, it never names evaluate_math as the tool to use for a single expression, so the choice between the two evaluators must still be inferred.

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

All Graph Paper 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?