Annotate text with known entities from a knowledge graph in read-only mode. A cold cache may return no annotations, so treat empty results as inconclusive.
Annotate text with known entities, read-only. A busy cold cache may return no annotations; that is not an absence proof.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| confidence | No |
Changes observed during successful MCP inspections.
v0.17.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description then adds real value beyond them: it warns that a busy cold cache may yield zero annotations and that an empty result is not proof of absence — exactly the kind of trap an agent would otherwise misread as a negative finding.
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?
Two short sentences, front-loaded with the action and followed immediately by the failure-mode caveat. Nothing is padded or redundant.
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 two-parameter, no-output-schema tool, the description covers the operation and the misleading-empty-result case. What it leaves out is the response shape (spans/offsets vs. entity list) and the meaning of the confidence parameter — noticeable but secondary gaps.
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 0%, so the description carries the full burden and does not compensate. It says nothing about what `text` should be (length, language, format) or what `confidence` controls (threshold direction, default, acceptable range), leaving the only tunable parameter unexplained.
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?
Names a specific verb and resource: 'Annotate text with known entities', plus a read-only qualifier. An agent can distinguish this from write/mutation siblings, though it does not name a nearest alternative (e.g. quipu_resolve_entity or quipu_entity_ref) despite a very crowded namespace.
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?
There is no explicit when-to-use guidance, no prerequisites, and no routing to alternatives among ~80 siblings that also touch entities. The intended use ('I have raw text and want recognized entities') is only loosely inferable from the purpose line.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.