Skip to main content
Glama

Compare visibility runs

compare-visibility-runs
Read-only

Compare 2-4 visibility runs across 1-20 slices in one table, at most 40 cells (runs × slices), each cell scored exactly as the Visibility page scores that run. A run is a run id or a YYYY-MM-DD day (that day's latest completed run, in time_zone). A slice is a prompt query type (branded = Branded, non_branded = Non-branded, competitor_branded = Competitor-branded; default non_branded), optionally narrowed by topic_id, custom filters (keys and value slugs from list-prompt-filters) and engine, with an optional row label. Each cell gives AI AuraScore (0-100), Mention Rate and Share of Voice (percentages, 0-100), Rank and Sentiment for the tracked brand. include_competitors adds competitor rows for the first slice, the top 30 by the newest run's Rank, with competitorsOmitted counting the rest; competitorSlice names the slice the competitor rows belong to. Runs come back oldest first. scopeTooSmall means the slice has too few prompts for an AI AuraScore or Rank; noAnswers means the run has no answers in that slice. A run's notes name scoring rules it predates; noteText explains them. An unknown slice key or a topic_id not on this domain is rejected. The result has one row per slice and one column group per run, labelled by its day. More than 4 runs is rejected. Without the Enterprise reporting entitlement, competitor Mention Rate is null and the units note says the plan withholds it; that null is not unmeasured.

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": {
      "domain_id": "<domain_id>",
      "runs": "<runs>",
      "slices": "<slices>"
    },
    "name": "compare-visibility-runs"
  }
}

Input Schema

NameRequiredDescriptionDefault
runsYes2-4 runs: run ids or YYYY-MM-DD days; returned oldest first
slicesYes1-20 slices: {label?, prompt_type?, topic_id?, filters?, engine?}; no other keys
domain_idYesDomain ID from list-domains
time_zoneNoIANA time zone that decides which day a run belongs to. Defaults to UTC.
include_competitorsNoAdd competitor rows for the first slice

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / domain_id / description
      Previous value: -"Domain ID"New value: +"Domain ID from list-domains"
  2. Changed4 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / domain_id / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • addedInput schema / properties / slices / items / properties / filters / propertyNames
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / slices / items / properties / topic_id / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only cover safety (readOnly, non-destructive, closed-world); the description adds substantial behavioral context beyond that: rejection rules, ordering ('runs come back oldest first'), result shape (one row per slice, one column group per run labelled by day), flag semantics (scopeTooSmall, noAnswers, notes/noteText), and an entitlement caveat explaining that a null competitor Mention Rate is a plan withholding, not missing data.

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 the core comparison contract, and nearly every sentence carries operational information (limits, cell contents, flags, entitlement). It is dense and long for a single paragraph, and the competitor/entitlement material could be broken out, but there is little outright filler.

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

Completeness5/5

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

With no output schema, the description carries the full burden of describing returns and does so: cell metrics, competitor row construction and competitorSlice, competitorsOmitted, ordering, and per-cell degradation states. An agent can predict both the success shape and the failure modes without additional sources.

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

Parameters5/5

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 well beyond it: it decodes each prompt_type enum value in human terms, states the non_branded default, points at list-prompt-filters as the source of filter keys and value slugs, explains that time_zone decides which day a run belongs to, and defines how include_competitors selects rows (first slice, top 30 by newest run's Rank).

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?

Opens with a specific verb + resource + hard scope: 'Compare 2-4 visibility runs across 1-20 slices in one table, at most 40 cells.' An agent immediately knows this is a multi-run comparison view rather than a single-run score lookup. It does not name the sibling it replaces (get-visibility-score, list-visibility-runs), so it stops short of a 5.

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 constraints are well specified (2-4 runs, 1-20 slices, >4 runs rejected, unknown slice key rejected), and defaults are stated (prompt_type defaults to non_branded). However there is no explicit statement of when to prefer this tool over get-visibility-score or get-visibility-summary, so selection guidance is only implied.

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.

Resources