list_keywordsList keywords tracked for a project — text, difficulty, intent, volume bucket (no_traffic | long_tail | average | high). Paginated; supports sorting and intent filter.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | Yes | ||
| cursor | No | ||
| context | Yes | One sentence: what is the operator trying to achieve right now? Describe their goal, not this tool's purpose. | |
| filters | No | ||
| sorting | No | ||
| projectId | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / contextAdded value: +{
+ "description": "One sentence: what is the operator trying to achieve right now? Describe their goal, not this tool's purpose.",
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "projectId",
- "limit"
-]New value: +[
+ "projectId",
+ "limit",
+ "context"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation as read-only, and the description adds useful behavioral context beyond that: pagination, support for sorting, the intent filter, and the volume bucket vocabulary. It reveals list semantics without contradicting the readOnlyHint.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded, covering what the tool lists, the fields returned, volume buckets, pagination, sorting, and filtering in two sentences. No filler or redundant restatement of the tool name appears.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description responsibly names the returned fields and pagination behavior. It leaves minor gaps around cursor usage and the exact response envelope, but for a paginated list tool the description is sufficiently complete for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 17%, so the description must compensate for undocumented parameters. It partially does by mentioning sorting and intent filtering, but it does not clarify cursor mechanics, limit behavior, or projectId semantics beyond what the schema already exposes through names, defaults, and enums.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') with a precise resource ('keywords tracked for a project') and enumerates the returned attributes and volume bucket values. This clearly differentiates it from the singular get_keyword_detail and other list tools by scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool: listing project-tracked keywords with pagination, sorting, and intent filtering. It does not explicitly name alternatives or exclusions, but the purpose is specific enough that an agent can infer when this list operation is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct resource and action, and the descriptions carefully cross-reference close alternatives (e.g., add_article_suggestion vs create_article_suggestion_with_input vs accept_idea). A few brief/read variants like get_article_brief, get_write_handoff, and download_brief_markdown could still be confused despite helpful explanations, so the set is not perfectly unambiguous.
Tool names follow a highly consistent verb_noun snake_case pattern throughout: get_*, list_*, create_*, update_*, set_*, add_*, delete_*, start_*, expand_*, etc. Even the less common names like lint_draft and remap_asset are still clear verb_noun constructions.
At 57 tools, this far exceeds the 50+ extreme threshold for a single MCP server. Even for a broad content workflow, the surface is overwhelming and would benefit from consolidation or splitting into focused servers.
The tool set covers the full content lifecycle: project setup, research runs, opportunity clustering, suggestion creation, brief generation, drafting, linting, publishing, reporting, and account management. Minor gaps exist—destinations and projects cannot be deleted via MCP, and there is no direct update for article suggestion metadata—but these are workable via the web UI or existing tools.