brain_submit

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

With no annotations, the description carries the full behavioral burden. It does disclose one genuine gate: an explicit resolution_of target is subject to the cloud writer's evidence and ACL checks. But it does not describe the write effect beyond 'submit'—whether it creates a new entry, updates existing content, or how rejection/failure surfaces—so the transparency is partial.

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?

Two sentences with no filler: the core action and payload constraint are front-loaded, and the second sentence earns its place by warning about resolution_of gating. Every sentence contributes essential information.

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?

The description resolves the hardest ambiguities: the exactly-one payload rule and the special gated behavior of resolution_of. An output schema exists, so return-value documentation is not required. It does not spell out the three remaining metadata parameters, but their names are conventional and lower-risk, making the tool largely usable as written.

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 is the only source of parameter meaning. It usefully clarifies that text/path/url form a mutually exclusive payload set and that resolution_of has validation/ACL implications. However, title, audience, and occurred_at are left entirely to name-based inference, leaving a gap in a 7-parameter optional 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?

The first sentence names a concrete action ('Submit'), a precise payload restriction ('exactly one text value, local file path, or URL'), and a destination ('team wiki'), which clearly separates it from the read/search/delete siblings in the tool list. The second sentence adds a meaningful caveat rather than blurring the purpose.

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?

The description implies a write/submit context through the verb and destination, and it explicitly states the exactly-one input rule. However, it gives no direct when-to-use guidance or alternatives such as 'use search_brain/read_page for retrieval.' The choice among brain_submit and its siblings is left mostly to inference.

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