netintel_embeddings

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses dimensionality (384), in-house hosting, no API key requirement, cost ($0.001/call), and a batch limit of 256 texts. It omits return format and error behavior, but the disclosed operational traits are substantial.

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?

Front-loaded with the most decision-relevant facts (what it is, dimension, cost, batching) in compact sentences. The trailing truncated fragment 'Pairs with /text/chunk…' is sloppy but minor.

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 3-parameter tool with no annotations, no output schema, and 0% schema coverage, the description covers behavior and cost well but leaves encoding_format undocumented and does not reconcile the 256-text batch claim with the string-typed input. Enough to invoke, 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 description coverage is 0% across 3 parameters, so the description must compensate. It partially does by explaining input_type values (query/passage for e5 retrieval), but encoding_format is never mentioned and the required 'input' is left undefined. It also claims batching up to 256 texts while the schema types input as a single string, leaving the batch mechanism 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?

States a specific resource and key attributes: multilingual 384-dim text embeddings served in-house. The 'no OpenAI dependency, no API key' framing differentiates it from netintel_openai, though it never explicitly contrasts with the similarly named netintel_v1_embeddings sibling.

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 is only implied: query/passage input types for retrieval (e5) and 'pairs with /text/chunk' suggest a RAG/chunking workflow. There is no explicit when-to-use statement or stated alternative for choosing between this and netintel_v1_embeddings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.