Skip to main content
Glama

A2A Defense & Monetization Gateway

certify_skill_safety

Audita estáticamente el código Python de un skill contra troyanos DY-Skill y llamadas a shell.

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": {
      "code_str": "<code_str>"
    },
    "name": "certify_skill_safety"
  }
}

Input Schema

NameRequiredDescriptionDefault
code_strYes
skill_nameNounnamed_skill

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden, but it does contribute one important behavioral fact: the audit is 'estática', meaning the code is inspected without being executed — a real safety signal an agent could not get from structured fields. However, it says nothing about whether 'certify' yields a pass/fail verdict or findings list, whether there are false positives, or what output to expect, which is a notable gap for a certification tool.

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?

A single, front-loaded sentence with no padding or redundancy; the core action and scope come first. It is efficient, though the description switches to Spanish while the tool name and parameter names are English, and the unusually specific term 'troyanos DY-Skill' is left undefined.

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 two-parameter tool with no annotations and no output schema, the definition covers the essential action and threat model but omits return values and the role of 'skill_name'. Since no output schema exists, the description should explain what a certification result looks like, which it does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it largely does not. It implies that the primary input is Python source code (mapping loosely to 'code_str'), but never names or explains either parameter, and 'skill_name' (with its 'unnamed_skill' default) is completely unaddressed — an agent gets no hint that a label can or should be supplied.

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?

The description states a specific verb and scope: 'Audita estáticamente' (statically audits) applied to 'el código Python de un skill', and names the two threat classes it checks for (DY-Skill trojans and shell calls). An agent can tell exactly what the tool does without opening the schema. It stops short of a 5 only because it offers no differentiation from any sibling or scope limit.

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?

There is no explicit when-to-use, when-not-to-use, or prerequisite information. The word 'skill' implies the caller has a skill's Python source to inspect, but nothing says whether it should be run pre-deployment, on untrusted submissions, or how it relates to the sandbox/execution siblings. Usage must be inferred entirely.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources