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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond them: what the briefing contains, the fixed English file/key conventions across all brains, frontmatter semantics (status: active|closed, context: folders always loaded), and that _decisions.md is handled by append_file. It does not mention permissions or result size/pagination, but the annotation coverage lowers the bar.

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 key directive ('Call FIRST...') is front-loaded, and the paragraph is information-dense with no filler. However, heavy parenthetical nesting and the trailing file-structure conventions make it a somewhat run-on block; some frontmatter detail is more domain reference than call guidance.

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 carries the burden of describing returns and does so (contents of the briefing plus the change history window). Annotations cover the safety profile and the required parameter is explained. It is complete enough to invoke correctly; only the exact shape of the returned briefing is left implicit.

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 coverage is only 50%: `workspace` is documented in the schema, but the required `unit` parameter has no schema description. The description compensates by defining `unit` ('path or name') and explaining what a unit is. This meaningfully fills the gap left by the schema for the required parameter.

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 defines the resource precisely (a unit = a folder containing _about.md, such as a client or project) and enumerates what the session returns: rules, _about.md, _ai.md, context, decisions, open sub-units, last 15 changes. It distinguishes itself from load_context, which it positions as the follow-up for sub-folders. The only weakness is that the actual act (producing a briefing) is implied by the content list rather than stated as a verb.

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 gives an explicit trigger ('Call FIRST when the user names a unit') and an explicit next step ('Then load_context on the sub-folder you need'), naming the sibling tool by name. The when-to-use and the hand-off are both spelled out, leaving nothing to inference.

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