Neurons Send

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

Beyond the annotations, the description discloses two high-value traits: a hard failure precondition (messages only travel over lines the user connected in the Neurons dashboard; without one this fails) and blocking semantics (`wait_seconds` blocks for the reply, up to the schema's 120s cap). It does not explain what a `proposal` triggers downstream or what happens when the wait expires without a reply.

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?

Dense and front-loaded: the routing targets come first, then fallback behavior, then the blocking caveat, with no filler sentences. The heavy inline quoting makes it slightly harder to scan than it needs to be.

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 an 8-parameter tool with no output schema and only three boolean annotations, the description covers routing, failure, and blocking well but leaves a third of the parameters undocumented and never says what the reply actually looks like or what happens on timeout. Adequate, with clear 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% across 8 parameters, so the description must carry the load. It explains `to`, `kind`, `local_first`, and `wait_seconds` well, but `refs`, `repo`, and `subject` receive no mention at all, and "keep it short" is vague next to the body's 8000-character maxLength.

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?

The description gives specific verbs (ask/tell/suggest) mapped to the three message kinds and enumerates valid targets ("codex", "claude", a handle, "all", "local"). It does not explicitly distinguish this from the sibling `reply` tool, so an agent must infer that `send` starts a conversation while `reply` continues one.

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?

It states when to pick each kind (question/note/proposal) and when to use "all" (for a second opinion) and "local"/"local_first" (free local model). What is missing is a when-not-to-use clause, particularly versus `reply` and `handoff_publish`.

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