Skip to main content
Glama

This week's SEO and AI search work

seo_set
Read-only

The week's set, picked from the stored search reads (seo_read), the crawl (seo_crawl) and the latest AI visibility run, so the founder does not choose item by item: title rewrites with the most clicks to win back, lifts onto page one, internal links anchored in each target's own best search, a refresh of a page that lost clicks, a new page for a search no page owns, the site fixes, a "what is" page and an AI info page when missing, AI answers lost with their gap, Bing, and in a product's first sets only, the first directories to list on (those AI answers cite for its buyers first). Each action says its routine step and what to record (record_action meta), so it is read at 28 and 56 days against the whole site. Also the reads of changes shipped before, and price: what doing the set costs (the research for each page it writes, the lists AI answers cite for a lost answer; the rest is code changes and free). This call is free.

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": "seo_set"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that the call is free, that `price` describes the cost of doing the set, that prior shipped changes are included, and that actions are read at 28 and 56 days against the whole site. That is useful behavioral context not derivable from the readOnly/openWorld annotations. It does not describe the return shape, but the cost and retrospective details are substantive additions.

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

Conciseness2/5

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

The description is a single sprawling sentence with many nested clauses and little front-loading. It is dense and difficult to parse, and several items are packed together without hierarchy. The content is valuable but the structure undermines readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and a zero-parameter composite tool, the description must explain what comes back. It enumerates the kinds of actions and mentions record_action metadata, cost, and follow-up reads, which is substantial. However, it never states the response structure or how the agent should interpret the returned set, leaving a meaningful gap for a tool of this complexity.

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?

The tool takes zero parameters, so there is no parameter semantics to clarify beyond the baseline. The description does not need to explain inputs and does not create confusion about them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the contents of the weekly set and names its sources (seo_read, seo_crawl, AI visibility run), which helps distinguish it from siblings. However, it never states the operation with a clear verb—'The week's set' is a noun phrase, leaving the agent to infer that this returns a curated worklist. The purpose is discoverable but not stated cleanly.

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?

It implies a weekly cadence and explains that the founder does not choose item by item, which gives some context for use. But there is no explicit guidance on when to call this versus seo_read, seo_crawl, or visibility, and no exclusions or prerequisites are stated.

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.