Skip to main content
Glama
RocqSolid
by bn-peters

Rocq Run At

rocq_run_at

Runs Rocq commands at a specified file position and returns their output, enabling queries such as Search, Check, About, and Locate plus proof-state inspection for debugging.

Instructions

Run Rocq commands at a file position and return their output.

Use this for running Rocq commands, such as:

  • Search Nat.add.

  • Search insert delete "_eq".

  • Check (3 + 4).

  • About Nat.add.

  • Locate "+".

  • Show. (to show the proof state at a position) The tool is also useful for one-off debugging tasks.

Prefer calling this tool right after imports or between lemmas/definitions. Only use within proofs when necessary.

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": {
      "file": "<file>",
      "commands": "<commands>",
      "line": "<line>"
    },
    "name": "rocq_run_at"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesAbsolute path to a .v file.
lineYes1-based line number in the file at which the commands string is ran.
commandsYesOne string containing one or more complete Rocq commands to run at the same file position, e.g. 'Require Import List. Check list.'
characterNo1-based column offset. Defaults to 1 (start of line).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It discloses that output is returned and that commands run at a specific file position, but it never says whether execution mutates or persists state in the file, whether it requires the file to be compiled/loaded first, or what happens when a command errors mid-string — material gaps for a tool that executes arbitrary Rocq commands.

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?

Purpose is front-loaded in the first sentence, followed by an example list and then usage guidance, so an agent can stop reading early. The example bullet list is slightly long for the value it adds, but every line is concrete rather than filler.

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?

With four fully documented parameters, an output schema, and no nested objects, the definition covers what the agent needs to call it correctly. The remaining hole is behavioral rather than structural: no statement about file mutation or execution preconditions.

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 100%, so all four parameters (file, line, commands, character) are already documented in the schema, including the 1-based conventions and the default column. The description adds only the loose notion of a 'file position' and the multi-command capability of the commands string, which the schema already states with an example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run Rocq commands at a file position and return their output'), which is clearly distinguishable from the sibling rocq_check_file by its positional targeting rather than whole-file checking. The concrete command examples (Search, Check, About, Locate, Show) sharpen the picture further, though the description never names the sibling as an alternative.

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?

Gives explicit placement guidance: prefer it right after imports or between lemmas/definitions, and only use it inside proofs when necessary. That is real when-to-use and when-not-to-use advice, but it never contrasts against rocq_check_file or any other route to the same information.

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

Deploy Server

Other Tools