Skip to main content
Glama

What to do next

get_actions
Read-only

What to do to get cited by AI, ranked like the dashboard. view: next = THE next step, with its steps and how to close it; plan = the full prioritized action plan; easiest_wins = sites cited in the answers the brand loses: where to get listed; site_audit = technical audit with paste-ready fixes (robots.txt, JSON-LD, meta tags); refresh true re-crawls; pruning = quarterly review: pages to improve, merge or remove; site_crawl = weekly crawl of the whole site: health, history, issues, every page; site_page = one page (url): issues, what the AI reads, questions citing it, links; impact = measured before / after of done actions and published articles. Read-only. Replies with metrics carry glossary: the dashboard's own explanation of each one.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoOnly for view next, plan, easiest_wins. End date YYYY-MM-DD. Default: now.
urlNoOnly for view site_page. The page address, as listed by get_actions view site_crawl.
fromNoOnly for view next, plan, easiest_wins. Start date YYYY-MM-DD. Default: all time.
langNoOnly for view next, plan, easiest_wins, site_audit, pruning, site_crawl, site_page. Language of the texts (default en).
viewNoWhat to return (default next).
brandNoBrand id, name or domain (from get_account (view: brands)). Optional when the account has a single brand.
issueNoOnly for view site_crawl. Optional: only the pages with this issue id (ids are listed in issues).
limitNoOnly for view plan, easiest_wins, site_crawl. Max items to return (the default and the maximum depend on the view; a larger value is capped).
engineNoOnly for view next, plan, easiest_wins. Optional AI engine filter, comma separated: chatgpt, gemini, perplexity, ai_overviews, ai_mode. Default: all engines.
offsetNoOnly for view easiest_wins, site_crawl. Items to skip, for pagination.
refreshNoOnly for view site_audit. true = crawl the site again now instead of reading the last audit.
url_containsNoOnly for view site_crawl. Optional: only the pages whose address contains this text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / issue
      Added value: +{
      +  "description": "Only for view site_crawl. Optional: only the pages with this issue id (ids are listed in issues).",
      +  "type": "string"
      +}
    • changedInput schema / properties / lang / description
      Previous value: -"Language of the texts (default en)."New value: +"Only for view next, plan, easiest_wins, site_audit, pruning, site_crawl, site_page. Language of the texts (default en)."
    • changedInput schema / properties / limit / description
      Previous value: -"Only for view plan, easiest_wins. Max items to return (the default and the maximum depend on the view; a larger value is capped)."New value: +"Only for view plan, easiest_wins, site_crawl. Max items to return (the default and the maximum depend on the view; a larger value is capped)."
    • changedInput schema / properties / offset / description
      Previous value: -"Only for view easiest_wins. Items to skip, for pagination."New value: +"Only for view easiest_wins, site_crawl. Items to skip, for pagination."
    • addedInput schema / properties / url
      Added value: +{
      +  "description": "Only for view site_page. The page address, as listed by get_actions view site_crawl.",
      +  "type": "string"
      +}
    • addedInput schema / properties / url_contains
      Added value: +{
      +  "description": "Only for view site_crawl. Optional: only the pages whose address contains this text.",
      +  "type": "string"
      +}
    • changedInput schema / properties / view / enum
      Previous value: -[
      -  "next",
      -  "plan",
      -  "easiest_wins",
      -  "site_audit",
      -  "pruning"
      -]New value: +[
      +  "next",
      +  "plan",
      +  "easiest_wins",
      +  "site_audit",
      +  "pruning",
      +  "site_crawl",
      +  "site_page",
      +  "impact"
      +]
  2. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, and the description mostly restates "Read-only" — no credit for that repetition. It does add genuine behavior beyond the annotations: refresh=true triggers a re-crawl rather than reading the last audit, limit values above the view-specific maximum are silently capped, offset enables pagination only on some views, and replies include a glossary of metrics. Those are useful but sparse for a tool whose views have quite different outputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded: the core framing comes first, then a single semicolon-delimited enumeration that maps one clause per view, followed by scope and return-value notes. Every clause carries new information despite the compressed, run-on style.

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 twelve-parameter, eight-view tool with no output schema, the description covers what each view returns, the refresh side effect, limit capping, and the metrics glossary, which is a lot of the burden. It does not describe the shape or volume of results per view, so an agent still learns the return format only by calling it.

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%, so the baseline is 3; the description earns above that by explaining what each view value actually produces and why refresh re-crawls, which the enum value alone does not convey. It still leaves out guidance on the brand parameter's fallback behavior and how 'from'/'to' defaults interact with each view beyond what the schema already states.

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 opens with a specific framing ("what to do to get cited by AI, ranked like the dashboard") and then defines each of the eight views by what it returns (easiest_wins = sites to get listed, site_page = one page's issues/links, impact = before/after of done actions). An agent can tell this retrieves prioritized recommendations, distinct from siblings like manage_actions (mutation) or get_visibility (metrics), though it never explicitly names the boundary with get_traffic/get_visibility.

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 effectively gives a when-to-use map by defining the semantics of each view value, so an agent can select 'next' for the single next step versus 'plan' for the full prioritized list versus 'site_audit' for technical fixes. There is no explicit when-not guidance or statement of which sibling to use for related metric questions, so it stops short of the top band.

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.