Skip to main content
Glama

Agent Capability Preflight

agent_capability_preflight
Read-only

Assess an unfamiliar public GitHub repository or approved MCP endpoint before deciding whether to trust/use it. Cost: 1 TEST via agent-market-lab-fake-v1. Returns deterministic ALLOW/CAUTION/REJECT decisions, assessment state, risk findings and scope uncertainty from bounded static/metadata analysis. ALLOW does not mean safe; no target code or tools are executed.

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": {
      "target": "<target>"
    },
    "name": "agent_capability_preflight"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetYes
target_typeNo

Output Schema

NameRequiredDescriptionDefault
decisionYes
evidenceYes
findingsYes
request_idYes
risk_scoreYes
analysed_atYes
limitationsYes
uncertaintiesYes
engine_versionYes
assessment_stateYes
collection_completeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnly/destructive annotations, it discloses cost ("1 TEST via agent-market-lab-fake-v1"), methodology ("bounded static/metadata analysis"), a hard safety boundary ("no target code or tools are executed"), and an interpretation caveat that ALLOW does not equal safe. That last point is exactly the kind of nuance annotations cannot convey.

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 most decision-relevant content (what it assesses, when, and the decision output) is front-loaded, with cost and caveats following. It is dense with internal terminology ("agent-market-lab-fake-v1", "assessment state", "scope uncertainty") that adds specificity at some readability cost, but no sentence is filler.

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?

For a two-parameter assessment tool with an output schema already documenting return values, the description supplies everything else an agent needs: trigger conditions, cost, non-execution guarantee, deterministic behavior, and the limits of the ALLOW verdict. No material behavioral gap remains.

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 description coverage is 0%, and the description does not name or explain `target` or `target_type` directly. It does compensate partially by enumerating the two target kinds (GitHub repository vs approved MCP endpoint), which maps onto the target_type enum, and by flagging the "approved" qualifier, but format constraints (URI, max length) are left entirely 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?

The description states a specific verb ("Assess") and a precisely bounded resource ("an unfamiliar public GitHub repository or approved MCP endpoint"), plus the decision the result feeds into ("before deciding whether to trust/use it"). It also names the output shape (ALLOW/CAUTION/REJECT), so an agent knows exactly what kind of answer to expect.

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?

Usage context is explicit: run it on an unfamiliar public repo or approved MCP endpoint prior to trusting or adopting it. The scope limits (public repos, approved endpoints, unfamiliar targets) act as implicit exclusions, but no alternative or follow-up path is named, so it stops short of full routing guidance.

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