reflect

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

With no annotations, the description carries the full burden. It usefully discloses that items are never auto-applied ("never auto-rebalanced", "not a batch to apply") and that the report prices the move (cortex N -> M). However, it never states explicitly whether reflect itself mutates the store or is strictly read-only, which is the key behavioral fact an agent needs.

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?

Front-loaded with what the tool does, but the single dense paragraph uses heavy em-dash clauses and unglossed domain jargon, making it harder to parse than necessary. Nothing is obviously redundant, yet the structure is not clean.

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?

There is no output schema, so the description must convey return content; it does describe the report's categories and the priced cortex move reasonably. It stops short of describing the report's actual shape or ordering, leaving a small gap for a report-only tool.

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 100%: the lone optional 'initiative' param is already fully documented in the schema, including the cross-initiative read / un-tagged mutation behavior. The description adds nothing beyond that, so the baseline 3 applies.

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 clear verb+resource ("Reflect on the store") and enumerates the concrete contents of the work-list: orphans, open reviews, stale chains, settled work, cloud sign-offs. It does not explicitly distinguish itself from maintenance-adjacent siblings like lint, hygiene, or overview, and undefined jargon (cortex, cold) slightly blurs 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?

Gives an explicit trigger ("Run it when a piece of work ends, and before a session stops") and clarifies how to act on the last two categories (judge one at a time, not a batch). It does not name alternative sibling tools to use instead for those follow-up actions.

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