Google Sites MCP

Overview Schema Source Related Servers Discussions Admin

Choose where the next blocks are inserted

gsites_set_insert_point

Sets where new blocks go on a Google Sites page: insert after a section number (0 = top) or append at the end, so a run of add_* calls stays in order without dragging blocks.

Instructions

EXPERIMENTAL - in a live test, after=0 placed the first block in the wrong spot and was slow (every move hops one position at a time); verify with gsites_list_sections after use. By default every gsites_add_* tool appends at the END of the page. Call this with after=N to insert right after section N (0 = very top of the page); the point then advances by itself, so a sequence of add_* calls stays in order. after=-1 restores 'append at the end'. Use it to put a table of contents or an intro at the top without dragging blocks around (dragging is slow on long pages).

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": {
      "after": "<after>"
    },
    "name": "gsites_set_insert_point"
  }
}

Input Schema

Name	Required	Description	Default
`after`	Yes	Section number to insert after (0 = top); -1 = append at the end

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Nov 5, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations already cover the non-readonly, non-idempotent, non-destructive profile, and the description adds genuinely useful state semantics: the insertion point auto-advances across successive add_* calls, and -1 resets it. It also discloses an experimental caveat (after=0 misplaced blocks in a live test) and recommends verifying with gsites_list_sections. The gap is that it never says what the call itself returns or whether the failure affects later moves.

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?

It is front-loaded with the experimental warning, then defaults, then the parameter mechanics, then the use case, which is the right order. A few clauses repeat the slowness idea ('was slow', 'dragging is slow on long pages'), so it is slightly longer than necessary.

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 one-parameter, stateful cursor tool with no output schema, it covers the default behavior, the reset case, the auto-advance consequence, the experimental risk, and the verification tool. Nothing needed to call it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100% and the schema already defines after, 0, and -1, so the baseline is 3. The description goes beyond it by explaining that the point persists and advances on its own between calls, which is meaningfully more than 'section number to insert after'.

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 concrete verb and object ('Call this with after=N to insert right after section N') and frames it against the default behavior of every gsites_add_* sibling, which appends at the end. An agent can tell immediately what this tool changes and how it differs from the add_* and move_section siblings.

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?

It gives explicit when-to-use ('put a table of contents or an intro at the top'), when-not-to ('without dragging blocks around', dragging is slow on long pages), and a reset case (after=-1 restores append-at-end). The alternative path (moving sections manually) is named and discouraged with a reason.

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