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

Annotations only declare readOnlyHint=false, destructiveHint=false and idempotentHint=true; the description earns credit beyond them by explaining exactly what the non-destructive outcome is: the old memory leaves default recall but retains history. It also documents the `undo` escape hatch that reverses the link, which is the behavioral detail an agent needs before mutating memory state.

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?

A single front-loaded sentence beginning with 'Use this when' delivers the trigger, the effect, and the reversal option with no filler. The semicolon-separated clauses are dense but readable.

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 annotations, a fully described schema, and an output schema covering return values, the description supplies the remaining essentials: trigger, effect on recall, history retention, and undo. It leaves unspecified whether both memories must already exist and whether a superseded memory can be superseded again, minor gaps for this tool's complexity.

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 100%, so both required parameters are already documented in structured fields, setting the baseline at 3. The description adds only modest meaning — clarifying that `memory_id` is the older memory being superseded and that `undo` removes the link, which largely restates the schema's 'Remove the link instead.'

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 names a specific verb+resource ('supersede' on `memory_id`) and states the resulting state change: the old memory leaves default recall but keeps its history. It implicitly separates the tool from forget_memory (which would remove it) and restore_memory, though it never names those siblings explicitly.

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 condition — use when a newer memory replaces `memory_id`, e.g. when `related` says 'updates' — which is concrete and actionable. It offers no explicit when-not guidance or named alternatives (correct_memory, forget_memory) for the disambiguation agent to compare against.

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