memory_reroute

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

With no annotations, the description bears full burden. It discloses destructive behavior ('relocates (destructive)') and notes read-only default. It mentions deterministic detection. However, it does not cover permissions, error cases, or data safety beyond noting destructiveness.

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 sentences, front-loaded with purpose, no fluff. Every sentence provides essential information. Very efficient.

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?

Given 3 parameters (0% schema coverage) and no annotations, the description covers destructive behavior and main parameters but misses 'sample_limit'. Output schema exists so return values are not required. Overall functional but incomplete for the unseen parameter.

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 0% so description must compensate. It explains 'source_bank' (bank to scan) and 'commit' (whether to actually move) but entirely omits 'sample_limit' (integer, default 500). Without this, the agent cannot tell what sample_limit controls or how to use it.

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 states a specific action: 'Find memories misrouted to the wrong bank and propose relocating them.' It provides a concrete example ('infra content in global-user') and clearly distinguishes from sibling tools (memory_recall, memory_dedupe, etc.) by focusing on rerouting rather than recall, ingestion, or deduplication.

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 clearly indicates when to use the tool (detect misrouted memories) and contrasts read-only default with destructive commit=True mode. However, it does not explicitly compare to alternatives (e.g., when to use memory_dedupe vs this tool) or state when not to use it.

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