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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower. The description usefully adds that the fact is saved to the contact's timeline and 'persists across sessions', but says nothing about deduplication, the approval_id gate, or what recording an inference implies.

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?

Two sentences, front-loaded with the when-to-use trigger and the primary action, with no filler. The informal 'ppl' phrasing is the only slight cost to structure.

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?

An output schema exists, so return values need not be explained, and the description covers the core purpose, trigger, and persistence behavior. It leaves the choice between memory_kind 'recorded' and 'inference' unguided, which is a real but narrow gap for a 5-parameter 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%, including the enum on memory_kind and the meaning of approval_id, so the schema carries the parameter burden. The description adds only illustrative example facts and no format or intent guidance beyond the schema, which is the baseline 3 case.

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 and resource ('store' a 'fact about a person') grounded in concrete examples, which is far more useful than a tautology. It does not explicitly name the memory.search / memory.semantic.search siblings it might be confused with, so it stops short of full sibling differentiation.

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 a clear triggering condition ('when you learn a fact about a person in conversation') and an explicit alternative to avoid ('instead of keeping it in your own context'). It lacks any when-not guidance or pointer to memory.search for the read side, so the routing guidance is contextual rather than complete.

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