Skip to main content
Glama
sudomichael

Gizmo Analytics

verify_install

Read-onlyIdempotent

Check if the analytics tracking script is installed on a site by scanning its homepage and returning whether the tag was found.

Instructions

ANSWER FIRST for any 'is it working?', 'did the install work?', 'is Gizmo tracking my site?', 'verify analytics setup', 'check if it's installed' question — typically asked right after create_site / get_install_snippet. Fetches the site's homepage and scans for the tracker script. Returns one of: {installed: true} (script tag found, with the publicKey we issued), {installed: false, reason} (page loaded but no tag — usually means the snippet wasn't placed or the build wasn't deployed yet), or {error} (fetch blocked / timed out / Cloudflare challenge — common on sites behind strict bot defense; doesn't necessarily mean it's broken). Tell the user the result honestly: 'Confirmed working' if installed; 'Couldn't find the script — did you deploy?' if no_tag; 'Couldn't reach the site (Cloudflare / bot block) — but if events are landing in the dashboard you're fine' on error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
site_idYesInternal site UUID for the target site. Get one from list_sites.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYestrue when the probe reached the homepage. false when the fetch itself failed (blocked/timeout/etc.).
siteYes
urlYesThe URL the probe actually fetched.
installedNook:true only. true = tracker script tag found on the homepage. false = HTML loaded but no tag (see reason).
scriptSrcNook:true + installed:true only. The src attribute of the detected script tag.
hasDataKeyNook:true + installed:true only. true if the script tag carries a data-key attribute (which it should).
reasonNook:true + installed:false only. Why we didn't detect the tracker. no_tag = HTML loaded, no script tag. no_html = response wasn't HTML. non_html_content = wrong content-type.
errorNook:false only. Why the probe couldn't reach the site. blocked / cloudflare don't necessarily mean the install is broken — many real sites have bot defense.
detailNook:false only. Free-form detail about the fetch failure.
retryAfterSecondsNook:false + error:rate_limited only. Seconds the server asked us to back off.
Behavior5/5

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

Annotations already indicate safe, non-destructive, idempotent behavior. The description adds detailed behavioral context: it fetches the homepage, scans for the script, and describes three possible return outcomes (installed, no_tag, error) including edge cases like Cloudflare blocks.

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 verbose but well-structured, starting with usage guidance, then behavior, return values, and user-facing advice. Every sentence adds value, though it could be slightly more concise.

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?

Given the output schema exists and the description thoroughly covers return values, edge cases, and user guidance, the description is fully complete for this tool's context. Sibling tools are mentioned for context.

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?

The input schema has 100% coverage with a clear description for site_id. The tool description does not add additional parameter semantics beyond what is in the schema, but schema coverage is sufficient, so baseline 3 is appropriate.

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 clearly states it verifies if the tracker script is installed by fetching the homepage. It explicitly distinguishes from siblings by positioning itself as the 'answer first' tool for installation verification, contrasting with create_site and get_install_snippet.

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 explicitly tells when to use this tool ('ANSWER FIRST for any 'is it working?') and in what context (right after create_site/get_install_snippet). It provides guidance on interpreting results and what to tell the user, offering clear alternatives for different outcomes.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sudomichael/gizmoanalytics-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server