STRG.com s3-compatible object storage for people and agents

Ask a question about STRG

ask_question

Read-only

Answers a how-to question about STRG and integrating with it - an SDK's configuration, an S3 operation's behaviour on STRG, where STRG differs from AWS S3 - from STRG's documentation, the S3 API reference, AWS's documentation, rclone's and s3cmd's documentation, and the web, with sources. It cannot see or change your buckets, objects or keys. A few questions a minute and a daily budget per user; the docs tool is not limited.

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": {
      "question": "<question>"
    },
    "name": "ask_question"
  }
}

Input Schema

Name	Required	Description	Default
`context`	No	What you are integrating with - language, SDK and version, tool, the error you got
`question`	Yes	The question, in natural language

Output Schema

Name	Required	Description
`answer`	Yes
`sources`	Yes
`webSearched`	Yes	Whether the web was searched - true with no web sources means nothing found was linked
`excerptsFrom`	No	The indexed sources whose excerpts the model read, linked or not - each third party's licence notice applies

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the two things an agent most needs: a hard capability boundary (no access to buckets, objects or keys) and concrete rate limits ("a few questions a minute and a daily budget per user"), plus the contrasting unlimited docs tool. It also states answers come with sources, which is behavioural context the annotations do not carry.

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?

Three sentences, all load-bearing, with the capability statement and rate limits front-loaded after the purpose. The second sentence is a dense run-on enumerating sources, but no sentence is filler.

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 read-only Q&A tool with an output schema and full annotation coverage, the description supplies the missing pieces: scope of answerable questions, source material, capability limits, and throttling. Only edge behaviour such as what happens when the daily budget is exhausted is left unstated.

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 100%, so both the question and context parameters are already documented with lengths and purpose. The description adds nothing about how to shape the question or what belongs in context, so it sits at the baseline for a fully annotated 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 opens with a specific verb and resource ("Answers a how-to question about STRG and integrating with it") and then enumerates the exact question shapes it covers: SDK configuration, S3 operation behaviour on STRG, and STRG/AWS S3 differences. That scope statement lets an agent separate it from the sibling docs and execute_s3_operation tools without inspecting either schema.

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 clear: how-to and behavioural questions answered from documentation and the web, with the explicit exclusion that it "cannot see or change your buckets, objects or keys" routing operational work to execute_s3_operation. It also names the docs tool as a less-constrained alternative ("the docs tool is not limited"), though it stops short of saying when to prefer that tool outright.

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

All STRG.com s3-compatible object storage for people and agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?