get_benchmarkWhere this business sits against every other measured business in its category: rank, percentile, and the distribution above and below. Real corpus, not an estimate.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers the safety profile, and the description adds useful behavioral context by explaining that the result is based on a real corpus, not an estimate. It also mentions the distribution above and below, which is a behavior of the response. This is adequate but does not go into deeper detail about data freshness or category definitions.
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 two sentences with no unnecessary information. The main output is stated upfront, and the clarifying 'Real corpus, not an estimate' is short and value-adding. Every sentence earns its place.
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?
This is a simple read-only tool with no input parameters, so the description is mostly sufficient for an agent to select and invoke it. It explains what the tool returns and the nature of the data. The main gap is the lack of a more precise definition of 'measured category' and the exact shape of the distribution data, but the low complexity keeps the omission minor.
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?
The tool has zero parameters and the schema is effectively empty, so there are no parameter semantics for the description to clarify. The description compensates by explaining what the output means, which helps an agent interpret the returned rank, percentile, and distribution. This meets the baseline for a no-parameter tool.
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 clearly states what the tool does: it positions the current business against all other measured businesses in its category and identifies the exact outputs (rank, percentile, and distribution above/below). The phrase 'Real corpus, not an estimate' further clarifies the data source. This distinguishes it from other sibling get_* tools that focus on traffic, mentions, or share of voice.
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 implies when to use it: whenever an agent needs a category benchmark based on actual measured data rather than estimates. However, it does not explicitly state when-not-to-use it or name alternatives such as get_rivals or get_share_of_voice. The usage context is clear but not differentiated from siblings.
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 have clearly distinct objects: answers, trajectories, citations, mentions, traffic, scores, and briefs. A few pairs like get_citation_sources vs get_source_profile and get_rivals vs get_share_of_voice overlap thematically, but their descriptions clarify different granularity and purpose.
All 16 tools follow an identical get_ + snake_case noun phrase pattern, such as get_agent_view, get_share_of_voice, and get_question_trajectories. This makes the tool set highly predictable and easy to navigate.
At 16 tools, the set sits just above the ideal 3-15 range, but each tool addresses a distinct facet of AI visibility monitoring. The count feels justified rather than bloated, though it is slightly heavy for a read-only monitor.
The suite covers the full read-only monitoring lifecycle: visibility scores, raw answers, question histories, competitor comparisons, cited sources, mentions, traffic, benchmarks, action plans, personas, and content briefs. There are no obvious dead ends or missing core operations for the stated purpose.