Extract clean text content from any URL. Use this when a user shares a link (competitor site, news article, client brief, trend report) and wants to cross-reference it against Fodda knowledge graphs. Returns structured text ready for analysis.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to read and extract content from | |
| userId | No | Optional user identifier for usage tracking. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already carry the readOnly, openWorld, idempotent, and non-destructive hints, so the description only needed to add behavioral context beyond that. It does so by saying the output is 'clean text' ready for analysis, which is genuinely useful for the agent. It does not mention potential failures on inaccessible URLs, but nothing contradicts the annotations.
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 concise and front-loaded: verb phrase first, then the trigger use case with concrete examples, then the output format. Every sentence adds value and there is no filler.
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?
The tool has one required parameter, no output schema, and useful annotations. The description explains what input is expected and what kind of result is returned, and the use-case grounding makes the agent's decision easy. It could add caveats about URL availability or authentication, but it is reasonably complete for this simple 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?
Schema description coverage is 100%, with a clear description for both url and userId. The description adds no parameter-specific semantics beyond the schema, but with full coverage it does not need to. A baseline of 3 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?
The description begins with a specific verb and resource: 'Extract clean text content from any URL.' It also communicates the tool's niche—ingesting external links—which distinguishes it from graph-focused siblings like get_node and search_graph.
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 explicitly says when to use the tool: when a user shares a link such as a competitor site, news article, client brief, or trend report and wants to cross-reference it against Fodda knowledge graphs. It does not name exclusions or alternative tools, but the use case is clear enough for an agent to select it confidently.
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.
The tools are largely distinct, with clear roles for discovery, search, evidence, node detail, neighbor exploration, supplemental data, visualization, and account checks. The main overlap risk is between brand_tracker and search_graph for brand-specific queries, but their descriptions steer usage toward different granularities.
Most tools follow a predictable verb_noun structure such as search_graph, get_node, list_graphs, and check_supplemental_status. The only clear outlier is brand_tracker, which is a noun phrase rather than an imperative verb_noun name.
13 tools cover a complete brand-intelligence workflow without feeling bloated: discovery, search, deep dives, evidence retrieval, supplemental context, visualization, account management, and external URL handling. Each tool has a real role in the overall pipeline.
The tool surface covers the full research journey: list_graphs, search_graph, get_node, get_neighbors, get_evidence, get_supplemental_context, check_supplemental_status, visual generation, and account/capabilities checks. This is a read-only intelligence domain, so the absence of create/update/delete tools is appropriate, not a gap.