Skip to main content
Glama

List the AI search visibility opportunities worth working on

visibility_list_opportunities
Read-onlyIdempotent

Returns the ranked work queue Hi, Moose builds from a project's stored AI search visibility results: the same rows as the Opportunities tab in the app. Each row carries a one-line headline, a summary of what is happening and numbered steps (what to do), written by a model that read the real AI answers and the pages involved (adviceSource "model"; rows the app has not written advice for yet fall back to a template headline and next step, adviceSource "template"), plus the priority with its reasons, how consistently the gap held across runs, the effort, the status the team set in Hi, Moose, and an opportunity id. Five kinds of row: create-coverage (no page of yours answers a prompt competitors win), improve-page (a page of yours is cited or is the closest match but the brand is left out, ranked behind or cited without being named), earn-inclusion (a third-party page the AI systems cite names competitors but not the brand), correct-description (answers repeat a claim about the brand that needs checking) and investigate-change (the brand was named or cited before and is not any more). Reads stored results only, over the last lookbackDays (default 7) compared with the window before it; it does not run new checks. Call it again with opportunityId to get the full evidence for one row: the steps, how we know (the model's reasoning, confidence and quotes from the answers and pages), every prompt and AI system with its state and answer id, competitors, pages cited instead, your page, flagged answers and what changed. The detail call writes the advice when the app has none yet, which can take a minute. Rows cover the tracked prompts on the tracked engines only; report the window and sample sizes plainly and never claim causation. Takes a few seconds to a minute.

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": {
      "project": "<project>"
    },
    "name": "visibility_list_opportunities"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many rows to return, best first. Default 10.
actionNoOptional: only rows of this kind.
projectYesThe Hi, Moose project, by its name as shown by list_projects. The projectId is also accepted.
priorityNoOptional: only rows with this priority.
lookbackDaysNoHow many days of stored results to read. Default 7, the same window as the Opportunities tab.
includeClosedNoOptional: also return rows the team marked done, dismissed or snoozed in Hi, Moose. Default false.
opportunityIdNoOptional: the opportunity id from an earlier result. Returns the full evidence for that one row instead of the list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations: discloses latency ('a few seconds to a minute'), the model-vs-template fallback with the adviceSource field, and the side effect that the detail call 'writes the advice when the app has none yet'. It also warns to 'report the window and sample sizes plainly and never claim causation'. The one wrinkle is that the disclosed advice-writing sits in mild tension with readOnlyHint=true, though it is a caching side effect that the description states openly rather than hides.

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

Conciseness3/5

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

Purpose is front-loaded and there is no filler, but the body is one dense run-on paragraph with a nested parenthetical about adviceSource buried inside an already long sentence. The five-kind enumeration and the detail-call guidance would be far more scannable as separated sentences or a list.

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 and does it: it describes every returned field group (headline, summary, steps, priority with reasons, consistency, effort, status, id), the detail-mode payload, the row taxonomy, the window comparison, and latency. Nothing an agent needs in order to call this correctly and report on it is missing.

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; the description beats that by giving each action enum value real meaning (e.g. improve-page = 'a page of yours is cited or is the closest match but the brand is left out, ranked behind or cited without being named') and by explaining lookbackDays is 'compared with the window before it'. It also clarifies that opportunityId switches the response from a list to a single row's evidence, which the schema only hints at.

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

Purpose5/5

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

Names a specific resource ('the ranked work queue ... built from a project's stored AI search visibility results') with a concrete analogy ('the same rows as the Opportunities tab in the app'). It also enumerates the five row kinds, which lets an agent distinguish this from siblings like visibility_list_results or visibility_get_summary before opening any schema.

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?

Explicitly bounds when to use it ('Reads stored results only ... it does not run new checks') and routes the agent to the detail path ('Call it again with opportunityId to get the full evidence for one row'). It also scopes coverage ('tracked prompts on the tracked engines only'). What it omits is a direct contrast with visibility_list_results, so the agent must infer which list tool to prefer.

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