Check if deep research is complete and retrieve the final report. Call this after deep_research_topic — poll every 10 seconds until status is COMPLETE or FAILED.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | The Job ID returned by deep_research_topic |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, making the tool safe to poll. The description adds essential behavioral context: polling every 10 seconds until COMPLETE or FAILED, which justifies repeated calls.
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?
Two concise sentences front-loaded with purpose and crucial usage instructions. Every sentence adds value with no redundancy.
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?
For a simple polling tool with one parameter and no output schema, the description sufficiently covers invocation, polling strategy, and termination conditions. Minor omission: does not mention possible error handling or retry logic, but overall complete for the task.
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 (job_id) with full schema description coverage (100%). The description adds no new semantic value beyond what the schema already provides ('The Job ID returned by deep_research_topic'). Baseline score is appropriate.
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?
Description explicitly states the tool checks if deep research is complete and retrieves the report. It uses a clear verb ('Check') and resource ('deep research status'), and distinguishes itself by referencing the initiating tool and polling behavior.
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?
Clearly states when to use (after deep_research_topic) and provides polling frequency and termination conditions. Does not explicitly mention alternatives (like check_supplemental_status), but the guidance is sufficient for correct usage.
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 roles: graph discovery, graph search, node detail, neighbor mapping, evidence retrieval, deep research launch, and status polling are all identifiable. The main ambiguity is between search_graph and get_label_values(label='Trend') for listing trends, and between deep_research_topic's built-in supplemental coverage and get_supplemental_context.
The set largely follows a snake_case verb_noun pattern such as search_graph, list_graphs, get_node, read_url, and generate_visual. The outlier is deep_research_topic, which is noun-led rather than verb-led, and get_my_account is a minor deviation from the pure verb_noun pattern, but neither seriously disrupts usability.
14 tools is well-scoped for a deep-research platform: graph discovery, graph search, retrieval, evidence, supplemental data, status polling, visualization, URL ingestion, and account/capability helpers all earn their place. The set feels like a deliberate pipeline rather than a miscellany.
The research lifecycle is well covered: discover graphs, search, explore trends, get supporting evidence, add supplemental data, launch deep research, poll status, and generate visuals. Minor conveniences like canceling or listing past research sessions are missing, but there are no dead ends for the core workflow.