FigTreeKit-MCP

run_figtreekit_cli

Execute the figtreekit CLI with arbitrary arguments to validate, analyze, style, export, or render phylogenetic trees, redirecting outputs into a run directory.

Instructions

Run the figtreekit CLI with arbitrary argv (full CLI coverage; no shell). Outputs are redirected into the run directory; each rewrite is disclosed in rewrites.

Args: argv: The figtreekit arguments as an array. Use <input> as a placeholder consumed by tree_content / input_file. tree_content: If provided, written as run_dir/input.tre and replaces <input> in argv. input_file: Or a whitelisted file reference (same placeholder rule). timeout: Max execution seconds (default 300). capture_tail_bytes: Max bytes of stdout/stderr kept (default 64 KiB).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "run_figtreekit_cli"
  }
}

Input Schema

Name	Required	Description	Default
`argv`	No
`timeout`	No
`input_file`	No
`tree_content`	No
`capture_tail_bytes`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 20, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does meaningful work: it discloses 'no shell', output redirection into the run directory, and rewrite tracking in ``rewrites``, which an agent needs to interpret results. It omits permissions side effects and whether the run directory persists or is discoverable, keeping it below 5.

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 behavior is front-loaded in the first sentence, and the Args block is terse and information-dense. No filler, though the docstring formatting is slightly redundant with the schema.

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 complex arbitrary-CLI tool with an output schema already covering return values, the description supplies the non-obvious pieces: placeholder substitution, redirection, rewrite disclosure, and defaults. It is essentially complete, though guidance on interplay with sibling tools is absent.

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 0%, so the description must compensate, and it does: each of the five parameters is explained, including the ``<input>`` placeholder rule linking argv to tree_content/input_file and the defaults for timeout and capture_tail_bytes. Minor gaps remain (e.g. what a 'whitelisted file reference' means).

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 the figtreekit CLI with arbitrary argv') plus scope qualifiers ('full CLI coverage; no shell'), making it clearly the raw escape hatch. It doesn't explicitly name a sibling like render_tree to contrast against, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

The tool implies general-purpose CLI coverage, but the description never says when to reach for this versus the many focused siblings (render_tree, collapse_clade, etc.) or when-not to use it. No prerequisites or exclusions are given.

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