Keytomic

List SEO Audit rows

list_audit_rows

Read-only

Lists all rows of one target of a finished SEO Audit. Pass exactly one target: category and check for the rows of one check, such as every page a check flagged (check names come from get_audit with category), or subject and key for the evidence rows of one finding or limitation, such as every page or image it affects (keys come from get_audit or list_audit_findings). Page with cursor and nextCursor.

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": {
      "projectId": "<projectId>",
      "runId": "<runId>"
    },
    "name": "list_audit_rows"
  }
}

Input Schema

Name	Required	Description
`key`	No	The finding’s or limitation’s key, such as images.MISSING_ALT. Pass it with subject.
`check`	No	Check name, a key of the category report’s checks. Pass it with category.
`limit`	No
`runId`	Yes	SEO Audit to read, from list_audits or get_audit.
`cursor`	No	nextCursor from the previous page. Leave it out for the first page.
`subject`	No	Whether key names a finding or a limitation. Pass it with key.
`category`	No	Category of the check. Pass it with check.
`projectId`	Yes	Site to read, from list_sites. Its SEO Audits are read.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds value the annotations do not: the audit must be 'finished', exactly one target must be supplied (the schema does not enforce mutual exclusivity), and results are paginated via cursor/nextCursor. It does not describe the shape or ordering of returned rows.

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-loaded with purpose, then addressing modes, then pagination, in three tight sentences with no filler. The nested parentheticals make it dense and slightly choppy to parse, but every clause carries information.

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 8 parameters, no output schema, and openWorldHint=true, the definition covers addressing and pagination but leaves the agent unaware of what a 'row' contains or whether row volume should drive limit choice. It also does not state what happens if the run is not yet finished, which the 'finished' prerequisite implies is a failure mode.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88%, so the schema already documents most parameters, and this sets a baseline of 3. The description does add pairing semantics ('Pass it with subject', 'Pass it with category') that the flat schema cannot express, which is genuinely useful beyond the structured data.

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?

States a specific verb and resource ('Lists all rows of one target of a finished SEO Audit') and immediately names the two addressing modes (category+check, subject+key) with examples of the rows each returns. It does not explicitly contrast itself with nearby siblings like list_audit_findings or list_audit_pages, though it does name them as sources of keys rather than as alternatives.

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 clear operating instructions: 'Pass exactly one target' followed by the two valid combinations, and cites get_audit as the source of check names and get_audit/list_audit_findings as the source of keys. It lacks an explicit when-not clause or a direct comparison against the sibling list tools, so the routing decision still requires inference.

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

All Keytomic 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?