decode_htmlDecode HTML entities (named like & and numeric like © / ©) back to plain text. Keyless, offline.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text containing HTML entities. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, which covers the safety profile. The description adds the behavioral attributes 'Keyless, offline' and clarifies the output is plain text, providing context beyond the annotations. It does not describe potential errors or edge cases, but for a simple transformation this is adequate.
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 one sentence, front-loaded with the action 'Decode', and contains no unnecessary words. Every piece of information (named versus numeric entities, keyless, offline) is meaningful and contributes to understanding.
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 one required parameter, no output schema, and good annotation coverage, the description fully covers what the tool does, what input it expects, and its key behavioral characteristics. No additional return value explanation is needed since the transformation 'back to plain text' is self-explanatory.
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?
The schema has 100% coverage for the single parameter 'text', with a description 'Text containing HTML entities.' The tool description adds value by giving concrete examples of entity formats (named like & and numeric like © / ©), which helps the agent understand the expected input beyond the schema's generic description.
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's function: decoding HTML entities (both named and numeric) back to plain text. It uses a specific verb 'decode' and identifies the resource (HTML entities). It is also distinct from the sibling tool encode_html, which performs the inverse operation.
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 clear usage context by noting 'Keyless, offline', indicating no authentication is required and the operation works offline. While it does not explicitly mention alternatives or exclusions, the context is sufficient for a simple utility tool. It lacks an explicit 'when not to use' statement, but it is implied that this is for decoding, not encoding.
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.
Multiple tools overlap heavily: ask_pipeworx, ask_pipeworx_beta (currently identical), and ask_pipeworx_grounded share the same routing core, while bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_fill_risk all target prediction-market edge detection. The descriptions are detailed, but an agent must read a lot of nuance to avoid selecting the wrong tool.
All names are lowercase snake_case and readable, but the convention is mixed: verb_noun names like encode_html and resolve_entity sit alongside bare verbs like remember and forget, and noun-phrase names like entity_profile, recent_changes, and polymarket_fill_risk. The ask_pipeworx_* and polymarket_* families are internally consistent, but there is no single predictable pattern across the whole set.
At 33 tools this exceeds the 25+ threshold for a heavy set. The bloat is especially noticeable because the server is named Htmlentities yet only encode_html and decode_html relate to that purpose; the rest are unrelated Pipeworx research, prediction-market, memory, and subscription utilities.
The Pipeworx surface is broadly complete: ask/grounded/deep_research/discover/suggest cover data access, entity_profile/compare_entities/recent_changes/validate_claim cover entity workflows, and subscriptions and memory have create/list/delete lifecycles. Minor gaps such as no update operation for subscriptions or memories are workable, and encode/decode fully covers the literal Htmlentities purpose.