Mark

Save Keywords

save_keywords

Idempotent

Saves keywords (from research or Search Console) and sets their tags, exclusion and rank tracking, in one call. New keywords are tracked and audience-checked (one Google top 10 fetch each) unless track is false or they are excluded. Exclude a keyword whose searchers aren't the buyer; it stops tracking. If this refuses because the workspace is not set up, call get_setup_status and check its rows, including skipped ones. Related: research_keywords, list_saved_keywords, set_up_market.

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": {
      "items": "<items>"
    },
    "name": "save_keywords"
  }
}

Input Schema

Name	Required	Description	Default
`items`	Yes	Keywords to upsert.

Output Schema

Name	Required	Description	Default
`saved`	Yes
`outcomes`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 1, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover idempotency, non-destructiveness and mutation, but the description adds real cost/latency context (one Google top-10 fetch per new keyword) and the consequence of exclusion ('it stops tracking'), which annotations cannot convey. It does not explain the upsert/merge behavior on existing keywords, which would complete the picture.

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?

Front-loads the core action in the first sentence, then the side effects, then the failure-recovery path. Dense but every sentence carries information; the get_setup_status sentence is slightly bolted-on but genuinely actionable.

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 an output schema present, return values needn't be described, and the description covers the non-obvious pieces an agent needs: per-keyword external fetch cost, tracking defaults, exclusion semantics, and the setup-failure route. Missing only explicit note on what happens to already-saved keywords when re-saved.

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 description coverage is 100%, so the baseline is 3; the description adds value by tying 'excluded' to stopping rank tracking and by clarifying that track=false or exclusion suppresses the fetch. It leaves source enum meanings and siteId/languageCode/locationCode to the schema, which is acceptable at full coverage.

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?

States a specific verb and resource ('Saves keywords') plus the scope of what it configures (tags, exclusion, rank tracking) and the sources it accepts (research, Search Console). It explicitly names what it is not — research_keywords, list_saved_keywords — so an agent can separate discovery from persistence without opening a 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?

Gives concrete routing: exclude keywords whose searchers aren't the buyer, and call get_setup_status if the tool refuses for workspace setup reasons. It also explains the default condition under which tracking and audience checks happen. No explicit 'use this instead of X' for the save path, so not a 5.

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

All Mark 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?