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

Annotations already declare a non-read-only, destructive, non-idempotent mutation, and the description usefully adds patch semantics ("Only supplied fields change"), which directly answers the natural worry that a destructive update wipes unsupplied fields. It does not address what happens to concurrent edits, permissions, or the destructive blast radius beyond that one clause.

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?

Three short sentences with the resource and its scope front-loaded, then the sibling alternative, then the partial-update guarantee. No filler, though the opening sentence could be tightened by using the exact field names.

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 destructive, non-idempotent mutation with no output schema and zero schema descriptions, the definition covers targeting and patch semantics but omits revision-conflict behavior and what a successful update returns or makes visible. It is usable but leaves an agent guessing on the concurrency path.

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 carry parameter meaning; it only loosely gestures at two of the three fields (preferences, summary) without stating their content or size constraints. The third parameter, expected_revision, is never mentioned, leaving the optimistic-concurrency contract completely undocumented even though it governs whether the call fails.

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 and resource ("Update the connected user's free-text goals/preferences or onboarding review summary") and explicitly separates it from the sibling save_experience. The only slight muddiness is the loose mapping between the prose ("goals/preferences", "onboarding review summary") and the actual field names ("preferences", "summary").

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 routes the agent away from this tool when the task is adding/correcting career facts, naming save_experience as the alternative, and warns that editing the onboarding summary does not update the experience bank. It stops short of describing when a caller should prefer this tool over a full profile read-modify flow, but the primary alternative is covered.

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