Serpier

get-seo-keywords

Read-only

Paginated tracked SEO keywords with latest ranks. Filters use SeoKeywordFilterColumnId: keyword, engine, country, tags, searchIntent, funnelStage, searchVolume, difficulty, desktopRank, mobileRank, foundUrl, serpFeatures. Optional segment: TOP_10, STRIKING, DROPPED, NOT_RANKING, LOSING_CLICKS, CANNIBALISED, LOW_CTR. Default limit is 50. Rank is 1-based; null means not ranking. previous* is the prior run.

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": {
      "advertiserProjectId": "<advertiserProjectId>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "get-seo-keywords"
  }
}

Input Schema

Name	Required	Description
`page`	No	1-based page number.
`limit`	No	Results per page (1-100).
`search`	No	Free-text search term; an empty string means no search.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`filters`	No	Column filters; each one narrows the results.
`orderBy`	No	Sort order: objects mapping one column id to 'asc' or 'desc'. Empty uses the list's default order.
`segment`	No	Only return keywords in this segment of the latest completed run. Counts per segment come from get-seo-segment-counts.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`advertiserProjectId`	Yes	Project id from get-projects or get-project.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), and the description adds genuinely useful behavioral context: rank is 1-based, null means not ranking, and previous* fields reflect the prior run. However, 'Default limit is 50' directly conflicts with the schema default of 20, which is actively misleading about result volume, and no pagination-exhaustion or result-shape behavior is described.

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?

Five short sentences, front-loaded with purpose, then filter vocabulary, segments, pagination, and rank semantics. No filler; every clause carries information an agent needs. The telegraphic 'previous* is the prior run' is terse but unambiguous.

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 9-parameter read-only listing tool with no output schema, the description covers the resource, filter vocabulary, segments, pagination and rank nullability. It stops short of describing what the returned records contain beyond ranks and previous* values, and the stated default limit disagrees with the schema.

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, but the description goes further by enumerating the valid SeoKeywordFilterColumnId values (keyword, engine, country, desktopRank, etc.) that the schema only exposes as a free string, and by naming the seven segment values with their meaning. It does not explain orderBy or the interaction between search and filters, which keeps it below a 5.

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 states a concrete verb and resource ('paginated tracked SEO keywords with latest ranks') and scopes it to the latest run data, so an agent can distinguish it from get-seo-keyword-detail or get-seo-segment-counts. It never explicitly names those siblings as alternatives, so differentiation is inferable rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: you page through tracked keywords, narrow with filters, and optionally restrict to a segment. There is no explicit statement of when to use this versus get-seo-keyword-detail for a single keyword or get-seo-segment-counts for segment sizes, and no prerequisites are given beyond the schema's advertiserProjectId note.

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

All Serpier 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.