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

Annotations only declare readOnlyHint=true, so the description usefully adds the failure mode (HTTP 500 while the index is building) and confirms distances are returned alongside neighbours. That is meaningful operational context beyond the annotation, though it says nothing about pagination or limits on the number of seed ids.

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 operational facts (semantic search, built-index requirement, 500 failure, follow-up tool) are front-loaded before the endpoint string. The 'This is what Atlas is for' sentence is mildly promotional and the raw HTTP path is developer-facing noise, but the core content is tight.

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?

With no output schema, the description at least indicates that neighbours and distances come back, and it covers the critical prerequisite for a successful call. It does not describe result shape or ordering, so an agent still lacks full expectations for the response.

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% and each parameter is already documented in the schema (k range 1-100, datum_ids as seed records, atlas_index_id sourced from nomic_get_dataset). The description only restates that ids are seeds for the search, adding no syntax or formatting detail beyond the schema.

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 verb+resource: given record ids, return nearest neighbours in embedding space with distances. It also distinguishes this lookup-by-id operation from the other nomic_* siblings, which are all getters for dataset/index/job metadata, and even names the underlying endpoint.

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?

Gives a clear precondition (a BUILT index is required) and routes the agent to nomic_get_index_job when the map is still building, which prevents a predictable 500. It stops short of naming alternate search tools or explicitly stating when not to use this one, so it is strong but not exhaustive.

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