Skip to main content
Glama

Search Fragments

Gate Probe

gate_probe

The gate before your agent answers. Call this FIRST for any question, before spending effort: one cheap look returns a routing verdict in a few seconds.

  • QUICK_LOOKUP: one page names the answer, with a quote copied from that page. Check the quote, then answer.

  • NEEDS_FULL_JOB: worth a full search. Call resolve_fragment with the user's words.

  • NOT_WORTH_IT: SF's one look found no page naming an answer, so a full search is unlikely to pay off (about 1 in 10 of these is still findable). Tell the user you cannot place it rather than guessing.

  • PROBE_UNAVAILABLE: the look failed. Treat as NEEDS_FULL_JOB.

Every outcome is a routing estimate about SF's own look, never a claim that the thing cannot be found.

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": {
      "fragment": "<fragment>"
    },
    "name": "gate_probe"
  }
}

Input Schema

NameRequiredDescriptionDefault
fragmentYesThe question or half-remembered thing, in the user's own words.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, the description discloses cost and latency ("one cheap look ... in a few seconds"), a failure mode (PROBE_UNAVAILABLE) with its prescribed handling, and an error-rate caveat ("about 1 in 10 of these is still findable"). It also bounds the epistemic weight of the result ("a routing estimate about SF's own look, never a claim that the thing cannot be found"), which is exactly the kind of nuance annotations cannot carry. One gap: annotations declare readOnlyHint=false while the description frames the call purely as a "look," and that mismatch is never explained.

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 opening line front-loads the decision rule, and the bulleted verdict list is scannable and each bullet carries a distinct action. There is mild redundancy between "about 1 in 10 of these is still findable" and the closing sentence about routing estimates, but the closing sentence is not a pure restatement since it constrains how the agent may report NOT_WORTH_IT. Overall tight for the amount of routing logic conveyed.

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?

With no output schema, the description correctly takes on the burden of enumerating the possible verdicts and what each one obliges the agent to do next, which is the critical missing piece. It also pre-empts the main misuse (treating NOT_WORTH_IT as proof of absence). What it leaves unexplained is the shape of the returned object and whether the few-second look can time out, but these are secondary for a single-parameter triage call.

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?

There is a single parameter and the schema already documents it fully ("The question or half-remembered thing, in the user's own words"), so the schema does the heavy lifting. The description reinforces the input intent by framing the call as something to do "for any question, before spending effort," implying the agent should pass raw user phrasing rather than a rewritten query. That is a useful but marginal addition over the 100%-covered schema, so baseline 3 applies.

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 gate before your agent answers" plus "one cheap look returns a routing verdict" states a specific function: a cheap pre-flight triage that returns one of four named verdicts. The four outcome labels (QUICK_LOOKUP, NEEDS_FULL_JOB, NOT_WORTH_IT, PROBE_UNAVAILABLE) make the tool's output space concrete and separate it from resolve_fragment, which is explicitly the deeper search. It stops short of 5 only because "probe" and "SF's own look" are metaphorical and the tool's actual mechanism is never named plainly.

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

Usage Guidelines5/5

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

The description gives an explicit ordering rule ("Call this FIRST for any question, before spending effort") and then routes each branch: QUICK_LOOKUP → check the quote and answer; NEEDS_FULL_JOB → call resolve_fragment with the user's words; NOT_WORTH_IT → tell the user rather than guess; PROBE_UNAVAILABLE → treat as NEEDS_FULL_JOB. The alternative tool is named together with the exact condition that selects it, leaving nothing to inference.

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.