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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses that the card is loaded into EVERY session (i.e. writes are persistent and globally impactful), that updates are shallow-merged with free keys accepted, and that get returns the card plus `fields` and `missing`. It adds a strong data-integrity constraint ('record ONLY what the user actually told you — never invent'), but says nothing about permissions or who may write.

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?

Content is front-loaded — what the card is, then why it matters, then per-op return semantics — and every clause carries information. It is dense with typographic quotes and parentheticals that add mild friction, but no sentence is filler.

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 3-param tool with no annotations and no output schema, the description covers purpose, persistence scope, merge semantics, and the shape of the get response. The only material omission is `_org`, plus any note on access control for a persistent, session-wide personalisation record.

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 0%, so the description must compensate, and it partially does: `op` is explained per value (get default → card + fields + missing; update → fields object) and `fields` gains real meaning as a key→value map that is shallow-merged with arbitrary keys allowed. The third parameter `_org` is never mentioned anywhere, leaving a genuine gap.

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 names a specific resource — the user's « situation with oto » profile card — and enumerates its contents (identity, job, goals, CRM, wanted connectors, tone preferences), so an agent knows exactly what data lives here. It does not explicitly contrast itself with near siblings such as oto_whoami, oto_identity or oto_context, 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?

It states a clear operating rule — re-read every session, keep it updated when you learn something useful, notably in the « Découverte » project — and sets op=get as the default path. What is missing is explicit routing against the other oto_* identity/context tools, so there is no stated when-not-to-use.

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