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

Beyond the destructiveHint/openWorldHint annotations, it discloses the actual write semantics: human overwrites anything, model overwrites only model, newer wins within a source, unknown keys are reported but do not abort the rest, and a model write over a human-stated trait returns why: person_said_it with current. That is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Front-loaded and generally well ordered, but it is long and contains a literal duplicated fragment ('the person stated it, `model` if you inferred it.' appears a second time dangling after the overwrite rules). That repetition costs clarity on the single most important parameter.

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 with no output schema, it covers the key whitelist, source semantics, overwrite conflict response, truncation limits in the schema, and the guest failure mode. Minor gaps remain: no statement of what a successful per-key answer looks like in full, or whether a returned unknown-key name means the call was partial.

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 the baseline is 3, but the description adds real meaning: the closed key whitelist, that source decides whether the write lands (not just a label), that value is a few words, and that recall is the one-line conversation outcome. It only stops short of operational detail such as what the per-key response looks like exactly.

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 stable traits about 'THIS person' so the next conversation does not start from zero, and names what it is not (name/email/phone, enquiry product/volume). It does not name the obvious read counterpart get_person_memory, so sibling differentiation is implicit rather than explicit.

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 explicit when-to-use (stable traits) and when-not (name, email, phone, product, volume, deadline, spec, with a reason for each exclusion), plus the guest case that returns sign_in_required. It also routes conflict handling: ask the person about the discrepancy instead of deciding for them.

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