html_to_textConvert HTML to readable plain text (keyless, offline): drops scripts/styles/comments, converts block elements to newlines, decodes entities, and collapses whitespace. Ideal for cleaning scraped HTML.
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | The HTML to convert. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses behavioral details beyond annotations (e.g., dropping scripts/styles, converting block elements) without contradicting annotations. Annotations already indicate safe, idempotent operation, and the description adds specific transformation rules.
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, front-loading the main action and then detailing specifics. Every sentence adds value without 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 tool with one parameter and clear annotations, the description fully covers its purpose, transformations, and ideal use case. No output schema is needed as return value is straightforward.
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 100% with one parameter 'html' described as 'The HTML to convert.' The description does not add extra meaning beyond the schema, so baseline 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 clearly states the tool converts HTML to plain text, listing specific transformations (drops scripts/styles/comments, converts block elements to newlines, decodes entities, collapses whitespace). It distinguishes itself from sibling tools by focusing on a specific utility.
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 provides context by noting it is 'keyless, offline' and 'ideal for cleaning scraped HTML,' implying when to use it. However, it does not explicitly state when not to use it or provide alternatives.
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.
Several tools form overlapping clusters (ask_pipeworx/ask_pipeworx_beta/ask_pipeworx_grounded, the five polymarket_* tools, and discover_tools vs suggest_questions) that could cause misselection on first glance. The detailed descriptions mostly clarify the boundaries, but the overlaps are real and require careful reading.
The naming is overwhelmingly snake_case with a verb_noun pattern (ask_, extract_, generate_, list_, resolve_, subscribe), which is predictable. A few noun-style or special-form names (entity_profile, html_to_text, recent_changes, polymarket_edges) break the pattern, but these are minor deviations.
At 34 tools the surface is heavy, especially for a server named 'Htmltext' where only 4 of 34 tools relate to HTML. Even accounting for the broad data/research domain, the set includes several redundant research and Polymarket helpers that push it past a well-scoped count.
The major subdomains are well covered: HTML extraction, entity/data research, prediction-market analysis, memory, and subscriptions all have the core operations needed with no obvious dead ends. Some niches are shallow (HTML lacks a general fetch/render tool; scan_dependency is a one-off), but agents can work around these gaps.