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

Beyond the annotations, the description discloses that records propagate to 'all four sites' and that 'nothing is ever deleted' — useful operational context for a write tool. The 'an identical record is not duplicated' clause largely restates idempotentHint=true, so part of the sentence is redundant with structured data rather than additive.

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 short sentences, zero filler, with the core action and content scope front-loaded before the cross-site and dedup behavior. Every clause carries information.

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?

For a two-parameter write tool with full schema coverage and complete annotations, the description covers what to store, the cross-site scope, and the no-delete/no-duplicate guarantees. The only minor gap is what a caller gets back on success, which is less critical given there is no output schema.

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 parameters (text with its 8000-character cap, role with its user/assistant enum and default) are already fully documented in the schema. The description adds no extra meaning for the role parameter, which controls attribution and is never mentioned in prose; 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 specific verb ('Save') and resource ('the user's AIfa memory') and enumerates the kinds of content that belong there (preference, decision, fact, session summary). The write verb implicitly separates it from the read-only siblings (memory_search, memory_recent, memory_about, memory_export), but no sibling is named explicitly, which keeps it from a 5.

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?

'Save something worth remembering' plus four concrete content examples gives an agent a clear inclusion test for when to call this. It stops short of stating when not to use it or pointing at memory_search/memory_recent for retrieval, so there is no explicit alternative routing.

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