Neurons Recall

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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is free. The description adds meaningful behavior beyond that: it enumerates the four corpora searched and makes clear the return is a list of "hits" requiring a second call to retrieve content — a non-obvious two-step interaction. It omits result ordering and the default of the limit parameter.

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?

Three short sentences, no filler: capability first, the use case second, the required follow-up last. Every sentence changes how the agent would call the tool.

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 and 0% schema description coverage, the description should work harder. It covers the search scope and the retrieval handoff, but an agent still cannot tell what limit defaults to or caps at, what repo_path does (and whether it is required when sources includes repo), or how hits are shaped.

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 must carry parameter meaning, and it only partly does: the four named corpora map one-to-one onto the sources enum (neurons, memory, sessions, repo), which is genuinely useful since the enum values are otherwise opaque. However, limit and repo_path get no mention at all, leaving half the parameters undocumented anywhere.

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 ("Search") and a precisely scoped resource set ("your memory files, past chats, Neurons notes and the repo"), with "YOUR OWN knowledge" drawing the boundary against external search tools like discover. The sentence "Open hits with recall_get" separates this search tool from its retrieval sibling without the agent needing to open either schema.

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 an explicit use case ("Use it to answer a peer's question") and an explicit follow-up step ("Open hits with recall_get"), which is clear routing guidance. It does not state when *not* to use it or name a competing search tool, so it stops short of full when/when-not coverage.

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