update_context

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

No annotations are provided, so the description carries the full behavioral burden and does so: it discloses upsert-by-key semantics, the destructive behavior of removing contradicted entries, cross-conversation persistence, auto-inference of category, and the encoding convention for tags. That covers mutation semantics and scope, which is more than structured fields supply here.

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-loads the purpose, then layers triggers, upsert rules, and conventions in a compact, scannable block. It is dense but nearly every clause carries an actionable rule; the long trigger list is justified by its role in proactive invocation, though it is the densest part.

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?

With no annotations and no output schema, the description supplies the semantics an agent needs: persistence scope, upsert/dedupe workflow, and how to populate optional fields. It stops short of describing what a successful write returns or how to recover from a failed upsert, but nothing essential to correct invocation is missing.

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 already 100%, so the baseline is 3; the description adds value by specifying the bilingual tag convention ("food"+"食物") and reinforcing that category should be inferred from content, going beyond the schema's own wording. It does not, however, add format or length guidance for key/value.

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+resource ('save user preferences, habits, and facts') and frames the tool as a personal memory system, which cleanly separates it from the sibling read/list/delete tools (get_context, list_contexts, delete_context). An agent can identify the operation without opening the 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?

Explicitly instructs when to call (PROACTIVE auto-call when the user reveals personal info), lists concrete EN and ZH trigger phrases, and prescribes prerequisites: check existing entries first, and delete contradicted entries before updating. This is when/when-not plus sequencing, not vague guidance.

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