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

Annotations already declare it is a non-read-only, non-destructive, idempotent, closed-world write. Beyond that, the description discloses the downstream effect ('Future drafts draw on it instead of making things up') and a hard authorship constraint, which are genuine behavioral traits not derivable from the annotations. It says nothing about duplicate handling, whether entries can be edited or removed, or what the call returns.

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, no filler. The what/where is front-loaded and the fabrication prohibition closes it, so the most consequential rule is the last thing read before acting.

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 an output schema present, return values need not be described, and the schema fully documents all four parameters. The description covers purpose, effect, and the core constraint, leaving only secondary gaps: duplicate/repeat behavior for an idempotent write, and the workspace-versus-personal-account scoping that the writer/workspace params imply.

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%, so the baseline is 3. The description goes slightly beyond the schema by defining what each enum value actually means in practice (a story they lived, a number they measured, an opinion they hold, an example they use), which reduces misclassification between 'opinion' and 'example'. The writer/workspace scoping parameters are untouched.

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+resource ('Save ... to their material bank') and enumerates the four material kinds (story, number, opinion, example), so the agent knows exactly what lands in the bank. It does not name a sibling such as save_voice_preference or update_voice_rule, so the boundary between 'material' and 'voice rule/preference' must be inferred from the resource noun alone.

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 trigger ('something real the writer has just told you') and an explicit exclusion ('Save only what the writer supplied; never add anything you wrote or assumed'), which is the key failure mode for this tool. It never names an alternative tool or states what to do when the writer's input is not real material, so routing against siblings is left implicit.

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