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

Goes well beyond the annotations: it explains partial-merge semantics, that a sent field replaces its saved value with no history kept (matching destructiveHint=true), which profile fields are server-owned and unwritable, that a daily routine enrolls the workspace in emailed check-ins, and what the response contains (saved/refused/warnings). This is exactly the extra behavior context annotations can't convey.

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 with what gets stored, then merge semantics, then stage values and caveats, then return shape. Dense but each sentence carries information; the long compound sentences are the only minor cost to readability.

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?

No output schema exists, but the description names the return fields, and annotations cover the destructive/idempotency profile. For a 5-parameter mutation tool it is nearly complete; the remaining gap is guidance on the many `patch` sub-fields, which are only documented inside the 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 description coverage is 0% at the top level, so the description must carry the load. It does well for `stage` (full enum listing), `routine` (email signup side effect) and `decision`, but the large `patch` object with dozens of writable profile keys is left to the nested $defs, and `session_note` is only alluded to. Partial compensation, not full.

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 verb (stores) and enumerates exactly what is persisted: business notes, onboarding stage, decision record, routine, and session note. It also states the payoff ('so a later conversation can continue from it'), which distinguishes it cleanly from the read-side sibling get_org_context.

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 a clear intended context — persisting what the user said so a later conversation can resume — and implicitly frames this as the write counterpart to reading context. It never explicitly names get_org_context as the alternative or states when not to save, so it stops short of full routing guidance.

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