Boot the brain

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

Annotations declare readOnlyHint=false, idempotentHint=true and openWorldHint=true; the description fills in exactly the missing detail — the only write is the boot stamp (plus brain creation on first use), shared-team-space sync may be offline and that is normal, and the returned protocol_enforcement block is binding. It also warns against a specific misuse (reporting recently_closed as pending), which is real behavioral guidance.

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 critical instruction is front-loaded in the first clause, and the dense enumeration of loaded blocks is informative rather than filler. It is a long, semicolon-heavy run-on that could be tightened, but every clause carries usable instruction.

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?

No output schema exists, and the description compensates by enumerating the returned blocks (hot topics, active context with open_items/recently_closed, recent_sessions, counts, protocol_enforcement, memory_discipline, retired_tools). An agent has everything needed to call it correctly and interpret the result.

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?

Zero parameters, so the schema-description baseline of 4 applies; the description correctly conveys that no input is required and instead explains the shape of what comes back (hot topics, active context, counts, retired_tools).

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+resource (reads/loads the persistent brain at session start) and defines its unique role relative to the 14 sibling tools by naming the session-start trigger and the paired closing tool, crbro_consolidate. An agent can place it without opening any 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?

Explicit and unambiguous: 'call it FIRST in every conversation, before any other work', with the consequence of skipping ('loses all context') and the complementary tool for session end. This is as clear as when/when-not guidance gets.

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