link_entities_to_wikidataNamed-entity recognition + canonical linking to Wikidata Q-ids.
Brainiall Entity Linker engine. Disambiguates 'Apple' the company from 'apple' the fruit.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Input text | |
| max_entities | No | Max entities to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive, so the safety profile is covered and the description does not contradict it. The description adds the disambiguation behavior but omits details like pagination limits or the exact return shape of Q-ids. No contradiction with 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?
Compact and front-loaded: the core capability is the first sentence, and the disambiguation example is in the third line. Loses a point for the wasted branding sentence ('Brainiall Entity Linker engine') that does not earn its place with useful information.
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?
Adequate for a simple 2-parameter tool whose annotations carry the safety profile. However, there is no output schema, and the description does not specify the return format beyond implying Q-ids — an agent cannot tell whether results include confidence scores, bounding offsets, or just ids. This gap keeps it short of complete.
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% — both text and max_entities are already documented in the schema, so baseline 3 applies. The description adds no parameter-specific detail beyond confirming the output is Wikidata Q-ids, which is more behavior than parameter semantics.
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?
States the function clearly: named-entity recognition plus canonical linking to Wikidata Q-ids. The disambiguation example ('Apple' vs 'apple') effectively differentiates it from the sibling extract_entities, which presumably only extracts mentions. Minor deduction for the branding phrase 'Brainiall Entity Linker engine,' which adds no functional clarity.
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?
Usage context is implied rather than explicit. The disambiguation example suggests when this tool is needed (when canonical identity matters), but the description never names extract_entities as the lighter alternative or states when not to use it. No explicit when/when-not routing.
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 map cleanly to distinct capabilities, and the descriptions make the intended use clear. A few adjacent pairs—extract_entities vs link_entities_to_wikidata and detect_pii vs detect_conversational_pii—require careful selection, but they are distinguishable by their stated outputs.
Names are uniformly lowercase snake_case and mostly follow a verb_object pattern, such as analyze_*, detect_*, extract_*, summarize_text, and translate_text. A few outliers like aspect_sentiment, fraud_feedback, and knowledge_ingest break the verb-first feel, but the overall pattern remains predictable.
At 22 tools, this is on the heavy side of the borderline range. Each tool has a distinct job, but the mix of core NLP, safety, fraud, health-checking, and knowledge-base management makes the surface feel sprawling rather than tightly scoped.
The core NLP coverage is broad: sentiment, toxicity, PII, entities, QA, summarization, translation, and groundedness are all present. However, the knowledge-base tools support ingest/list/query but no delete or update, creating a dead end when documents need correction or removal.