Skip to main content
Glama

run_self_seeded_control

Read-onlyIdempotent

Plants known cryptographic and decoy lines into a temporary directory copy, scans it, and reports per-style detection outcomes to assess robustness on known patterns.

Instructions

Plant known lines into a temporary copy of a directory, scan the copy, and say what the scan did with each: robustness on known patterns.

27 cryptographic uses in 9 styles (direct calls, aliased names, names built from pieces, calls split over lines, shell commands in strings, cert-manager, Terraform, Java properties, UTF-16 without a byte-order mark) and 18 lines that name an algorithm without using it (switched-off flags, deny lists, log strings, variable names, comments, a JWKS key label, an sshd_config removal list) per tree with one language. Returns self_seeded_control -- counts by style, by decoy class and by confidence, the seed, the harness digest -- and items, where each line went and its outcome.

Behaviour beyond the annotations: it writes the copy to a temporary directory and removes it afterwards; nothing in path changes and nothing leaves the machine.

Use it to learn which styles this instrument's silence may be relied on in this tree. Do not use it to inventory the tree -- that is scan_repo -- and do not read its counts as a statement about the tree's own cryptography: the denominator is what was planted, and the figure never makes claims.control.held true.

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": {
      "path": "<path>"
    },
    "name": "run_self_seeded_control"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesDirectory whose copy is planted and scanned, same argument as `scan_repo`. The directory itself is not written to.
seedNoChooses where each planted line goes. The same seed on the same tree plants the same lines at the same places.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.36.1

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond annotations: it discloses that a copy is written to a temporary directory and removed afterwards, and that ``path`` is untouched and nothing leaves the machine — clarifying how readOnlyHint holds despite a write to temp space. It also warns that the result never makes ``claims.control.held`` true, a real semantic constraint. Slightly short on error modes, but annotations plus this context cover the rest.

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?

Front-loads the operation in one sentence and follows with the details an agent needs (corpus composition, return shape, safety caveat). The dense parenthetical lists of styles and decoy classes are long but each item is doing work; some pruning of the parenthetical enumerations would sharpen it without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output shape is summarized (counts by style, decoy class and confidence, the seed, harness digest, plus `items`) alongside a full output schema, and the safety and interpretation constraints are stated. An agent knows what it gets, what it costs, and how not to misuse the numbers.

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 coverage is 100% and both parameters are documented, so the baseline applies. The description adds the useful note that one tree carries a single language and echoes the seed's determinism, but does not explain seed semantics beyond the schema's own description.

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?

States a concrete three-step operation (plant known lines into a temporary copy, scan it, report per-line outcomes) and quantifies the planted corpus (27 cryptographic uses in 9 styles, 18 decoy lines). It explicitly distinguishes itself from `scan_repo` by naming that sibling and warning against reading counts as inventory of the tree.

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 an explicit use case (learn which styles this instrument's silence can be relied on in a given tree) and an explicit exclusion (do not inventory the tree, that is `scan_repo`). It also guards against misreading the counts as evidence about the tree's own cryptography. Lacks guidance on when the seed matters for comparing runs, but context is otherwise clear.

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