Skip to main content
Glama

start_minima_search

Finds multiple distinct low-energy geometries of a molecule by repeatedly biasing the potential energy surface to avoid previously found minima, then refining each candidate on the true surface.

Instructions

Search for multiple distinct relaxed geometries (local minima of the PES).

Repeatedly relaxes from the starting structure on a PES biased to repel the minima found so far, then polishes on the true PES. kernel is 'flooding' (Gaussian bumps; sigma in Å, amplitude in eV) or 'deflation' (inverse-distance poles). New minima are deduped by energy_tol (eV) + rmsd_tol (Å) and each is registered as a new structure. Poll get_status for n_found/target; get_results returns the distinct minima (structure_id + energy), sorted by energy. Steerable via steer abort/pause (and set_fmax/switch_optimizer mid-relaxation).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
structure_idYes
calculator_idYes
n_minimaNo
kernelNoflooding
optimizerNoFIRE
fmaxNo
stepsNo
sigmaNo
amplitudeNo
energy_tolNo
rmsd_tolNo
patienceNo
step_delayNo
Behavior5/5

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

Despite lacking annotations, the description extensively discloses behavioral traits: biased PES, kernel types ('flooding'/'deflation'), deduplication logic, asynchronous polling, and steerability. This fully informs the agent of the tool's behavior.

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 description is a single paragraph of 5 substantive sentences, front-loading the purpose. It is concise with no wasted words, though it could be structured with bullet points for clarity.

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?

Given the tool's complexity (13 parameters, no output schema, no annotations), the description covers the algorithm, key parameters, and usage flow well. Minor gaps in parameter details prevent a perfect score.

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 description adds meaning to several parameters (kernel, sigma, amplitude, energy_tol, rmsd_tol, fmax, optimizer) but omits details for many others (structure_id, calculator_id, steps, patience, step_delay). With 0% schema coverage, more complete parameter explanation would be beneficial.

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 clearly states 'Search for multiple distinct relaxed geometries (local minima of the PES)', using a specific verb and resource that distinguishes it from sibling tools like start_relaxation (single relaxation) or start_md (dynamics).

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?

The description provides clear context on the tool's function (multiple minima search, asynchronous polling) but does not explicitly state when to use it over alternatives like start_relaxation. However, the purpose is clear enough to infer usage.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jkitchin/fairchem-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server