cluster_competitorsGroup competitor URLs by content similarity using TF-IDF cosine similarity, with optional embeddings, to reveal clusters of overlapping pages for analysis.
Group competitor pages by TF-IDF cosine similarity (embeddings optional via config).
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | ||
| urls | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry behavioral disclosure; it does reveal the core algorithm and that embeddings are optional, which helps predict behavior. It does not state whether the tool fetches pages, mutates anything, or what the return shape is, so transparency is partial.
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?
A single front-loaded sentence that states action, object, and method with no filler. The parenthetical config note adds relevant optionality without bloating.
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 tool with no annotations and no output schema, the description omits the return value, the role of k, and any relationship to sibling tools like scrape_page that probably supply page content. It is enough to guess the intent, but not enough to invoke confidently.
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 coverage is 0% and the description compensates only for urls by saying 'competitor pages'; k, the only other parameter, is never mentioned or tied to the clustering behavior. The method detail explains the computation but not what values k accepts should mean for the number of clusters.
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 opens with a specific verb ('Group') and resource ('competitor pages') and adds the similarity method ('TF-IDF cosine similarity'), so it is unambiguous. It doesn't explicitly contrast with siblings like compare_headings or content_gap_analysis, though the grouping intent is distinct enough.
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?
No sentence explains when an agent should choose cluster_competitors over a sibling, nor when the optional embeddings config should be used. The only hint, 'embeddings optional via config,' is a configuration detail, not a usage condition.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.