Neurons Memory Save

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

Annotations already declare the mutation and non-destructive profile, and the description adds real policy the annotations can't convey: no secrets should be stored, and peer facts require declared source plus recorded evidence. It leaves unclear whether an update via id overwrites body wholesale or what confirm_new does.

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, with the mode-to-parameter mapping front-loaded. The phrasing is telegraphic to the point of being slightly cryptic ('Facts from a peer need source=peer and evidence of what you verified').

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 11-parameter mutation tool with no output schema and no per-parameter documentation, the description covers the operating modes but not enough of the surface for confident invocation. The undefined confirm_new parameter is the clearest completeness hole.

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 11 parameters, so the description carries the burden and only explains id, archive, source and evidence. The remaining parameters, notably confirm_new, plus the roles of title vs body, tags, scope, type and repo, are left for the agent to guess.

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 set (save/update/archive) and resource (a note in YOUR Neurons memory), and even maps each mode to its controlling parameter (id, id + archive). It does not contrast itself with siblings such as recall or recall_get, so an agent must infer the boundary between writing and reading.

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?

Mode selection is spelled out explicitly via parameters: no id = create, id = update, id + archive = archive. It also gives a conditional rule for peer-sourced facts (source=peer plus evidence). It stops short of naming when to prefer this over sibling tools or when not to save at all.

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