Skip to main content
Glama
singlestore-mcp-server

singlestore-mcp-server

by jonasliesas

app_page

Read-only

Fetches HTML for a SingleStore MCP server app page and omits shared head, build, and vendor blocks the caller already has, reducing payload while returning current views after restart.

Instructions

HTML of one of this server's app pages (the workspace loads its views with this).

Tool results aren't cached by hosts, unlike resources/read, so views pick
up changes right after restart_server.

``head``: the caller's shared-head hash (its ``s2-head`` meta); when it matches,
the page comes without the shared head (``head_omitted``; the caller puts its own
copy in at SHARED_HEAD_MARKER). ``build``: the build the caller already has; when
it matches, only ``unchanged`` comes back. ``vendors``: vendor blocks the caller
already has (name -> data-s2-hash, e.g. CodeMirror from the SQL Editor's page);
matching ones are left out (``vendors_omitted``; the caller puts its copy in at
each VENDOR_HAVE_MARKER).

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": {
      "uri": "<uri>"
    },
    "name": "app_page"
  }
}

Input Schema

NameRequiredDescriptionDefault
uriYes
headNo
buildNo
vendorsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.11.0
    • addedInput schema / properties / vendors
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": {
      +        "type": "string"
      +      },
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Vendors"
      +}
  2. Changed2 schema fields changedv0.10.1
    • addedInput schema / properties / build
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Build"
      +}
    • addedInput schema / properties / head
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Head"
      +}
  3. Addedv0.8.1

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: it discloses the host-caching difference versus resources/read and specifies the deduplication protocol (head_omitted with SHARED_HEAD_MARKER, unchanged when the build matches, vendors_omitted with VENDOR_HAVE_MARKER). It also makes clear that the caller carries the responsibility of reinserting its own copies of shared head and vendor blocks. That is exactly the kind of non-obvious behavioral context the description should supply.

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 description is front-loaded with purpose, then the caching rationale, then the per-parameter protocol notes, so it reads in a sensible order and every sentence carries information. It is dense and uses RST-style double-backtick markup that adds visual noise, and the marker-related sentences pack several concepts together, which slightly hurts readability.

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 compensates by explaining the possible response shapes (full page, head_omitted, unchanged, vendors_omitted), which is what an agent most needs for a read tool. Annotations already carry the safe-read profile. The missing piece is guidance on the required uri argument, which is the one gap that could cause a mis-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?

Schema description coverage is 0%, so the description has to carry the parameter load, and it does define head (the caller's s2-head hash), build (the build the caller already has), and vendors (a name-to-data-s2-hash map, with CodeMirror from the SQL Editor's page as an example). However, the only required parameter, uri, is never explained: the description does not say what valid page uris look like, so an agent still has to guess how to invoke the tool correctly. The strong coverage of three optional parameters is offset by the gap on the mandatory one.

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 identifies a specific resource: the HTML of one of this server's app pages, and adds that the workspace loads its views with it, which tells the agent what it is for. However, it omits an explicit verb (fetch/return) and frames the statement as a noun phrase, so the exact action is inferred rather than stated. It does contrast itself with resources/read, which helps differentiate it from the resource-loading path.

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?

It gives clear context for when to use this over the alternative: tool results are not cached by hosts, unlike resources/read, so views see changes immediately after restart_server. That is a real routing rationale rather than a generic statement. It falls short of a full 5 because it never states when not to use it, or which app pages/uris are appropriate, so the agent must infer the eligibility criteria.

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

Deploy Server

Other Tools