check_report_statusPoll a deep research report by slug. Free. Returns status (generating / ready / failed); a failed report triggers the automatic refund of its launch charge. Deep reports typically take 10-20 minutes — poll every few minutes, not every few seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The slug returned by start_deep_report |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint: true), description states that a failed report triggers automatic refund of launch charge and that the tool is free. Adds useful behavioral context not present in structured fields.
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?
Three sentences, front-loaded with purpose, no wasted words. Efficiently conveys core usage.
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?
Given low complexity (1 param, no output schema) and good annotations, description fully covers behavioral info: polling interval, refund policy, free access. Complete for a polling tool.
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?
Only one parameter 'slug' with schema description 'The slug returned by start_deep_report'. Description says 'by slug' but adds no additional meaning beyond schema. Baseline 3 due to 100% schema coverage.
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 'Poll a deep research report by slug', identifying the specific verb (poll) and resource (deep research report). It distinguishes from siblings like start_deep_report and get_report_result.
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?
Provides explicit guidance on polling interval: 'Deep reports typically take 10-20 minutes — poll every few minutes, not every few seconds.' Also notes it's free. Does not explicitly mention when not to use or alternatives, but context implies it's for checking status after starting a report.
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.
Each tool serves a distinct function: fact verification, visibility check, review gap analysis, competitor scan, and deep research. The report-related tools (start, poll, fetch) are clearly separated by their roles. No two tools are easily confused.
All names use snake_case consistently. Most start with verbs like 'check_', 'get_', 'run_', or 'start_', though 'ping' and 'review_gap' deviate slightly. The pattern is predictable and readable.
Eight tools cover the domain of local business intelligence well: fact-checking, visibility, review comparison, competitor scan, and deep research. The count is neither too sparse nor overwhelming for the scope.
The tool surface covers core intelligence needs: fact verification, review comparisons, visibility checks, competitor scans, and deep research reports. Minor gaps like a tool to list businesses or manage multiple entities exist, but for single-business analysis it's nearly complete.