Skip to main content
Glama

Check mechanism

check_mechanism
Read-onlyIdempotent

Validate a full multi-step mechanism before drawing: catches invalid SMILES, unexpected radicals, unbalanced atoms or charges, and steps that don't start from the previous intermediate.

Instructions

Validate a whole multi-step mechanism before drawing it (no figure is shown). Checks every species (valid SMILES, unexpected radicals from a bracket atom missing its H, unstabilised methyl/primary cations, strong bases under acidic conditions and vice versa, doubly charged species), each step's atom and charge balance, and that every step starts from an intermediate produced by the previous step. Call it once with all steps, fix every [error], consider each [warning], then draw the steps one at a time with draw_reaction_step.

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": {
      "steps": "<steps>"
    },
    "name": "check_mechanism"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely new behavior: no figure is returned, it checks SMILES validity, stray radicals, unstable cations, acid/base incompatibility, double charges, per-step atom/charge balance, and intermediate chaining between steps. The severity model ([error] vs [warning]) is disclosed. It stops short of stating the exact return shape, which is the only real gap.

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 and the trailing sentence encodes the follow-up workflow, so the ordering is sensible. The single dense sentence enumerating six species checks is information-rich rather than wasteful, though the nested parenthetical makes it harder to scan than it could be.

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 one-parameter tool with a nested step array and no output schema, the description supplies what the schema cannot: what gets checked, that failures come back as [error]/[warning], and what to do next. Only the precise response structure and step/species caps are left implicit, which an agent can recover from the schema or the first call.

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?

The description ties the checking logic back to the inputs: the stray-radical rule explains when the `radical` flag is needed, and the acid/base rule explains how `conditions` is interpreted across steps. That adds meaning beyond the schema's per-field text. It does not explicitly state per-step limits (max 4 species, 12 steps) or that `conditions` is optional, leaving that to 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?

"Validate a whole multi-step mechanism before drawing it (no figure is shown)" gives a specific verb (validate), a specific resource (a multi-step mechanism), and explicit scope (whole mechanism, no rendering). The parenthetical immediately separates it from draw_reaction_step and the other drawing siblings, so an agent can choose without opening either 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?

The workflow is spelled out end to end: validate first, "Call it once with all steps" (implicitly not per-step), "fix every [error], consider each [warning]", then "draw the steps one at a time with draw_reaction_step." That names the alternative tool, the ordering constraint, and the severity-handling policy, leaving nothing to inference.

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