user_profile_record

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false, which already signal a safe non-destructive write), the description discloses genuinely non-obvious behavior: re-recording the same predicate supersedes the prior value rather than duplicating, and history is retained. That supersede-and-keep-history semantics is the key thing an agent must know before writing and is not derivable from the annotations.

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 compact sentences, zero filler. The core action and its examples are front-loaded, and the sibling routing note is placed last where it does least to interrupt the primary instruction.

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 write tool with no output schema, the description covers what gets written, what happens on conflict, and where non-user notes belong. It omits what the call returns and does not mention the origin_trust ceiling behavior, which the schema documents but the description never reinforces.

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 predicate/value/user_id are already fully documented with their own examples. The description's examples largely restate the schema, with only the supersede rule adding real semantics to 'predicate'. Baseline 3 is appropriate when the schema carries the parameter burden.

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: 'Record one durable preference of a specific end user', with concrete examples (timezone, language, 'prefers tea'). It also distinguishes itself from memory_store ('Notes not tied to a user') and implicitly from user_profile_get, so an agent can separate it from its closest siblings without opening a schema.

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?

The description names an explicit alternative with its selection condition: notes not tied to a user should go to memory_store. It implies the tool is for per-user preference capture, but does not state when to prefer it over user_profile_get or how it relates to memory_get_history for reading history.

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