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

Annotations already declare the write semantics (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the bar is lower. The description adds real value beyond them: it names the read-back path (get_user_profile), clarifies that each call stores exactly one insight, and imposes a consent requirement. It does not say what happens when the same insight is saved twice, which matters given idempotentHint=false.

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, both earning their place: the first establishes the action, target store, valid content types, and read path; the second establishes the consent gate. Nothing is redundant and the essential scoping information is front-loaded.

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 no output schema, the description covers the action, destination, read path, one-insight-per-call granularity, and the consent rule. The only meaningful gap is the lack of guidance relative to the overlapping 'remember' sibling and duplicate handling.

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% and the category enum is fully documented with per-value meaning, so the schema carries the load and a 3 is the baseline. The description restates the four categories in prose but adds no format, length, or example guidance beyond what the schema already provides.

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 uses a specific verb and destination ('Save one insight to the user's Achriom taste profile') and enumerates exactly what qualifies as an insight, plus names the sibling that reads it back (get_user_profile). It loses a point because it never distinguishes itself from the sibling tool 'remember', which an agent could reasonably confuse with this one.

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 and an explicit prohibition: use only when the user asks you to remember or agrees to an offer, and 'do not save things they have not chosen to keep.' That is stronger than most definitions. However, it offers no guidance on choosing between this and the sibling 'remember' tool, leaving the main ambiguity unresolved.

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