record_keyed_fact

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

With no annotations provided, the description carries the transparency burden. It clearly discloses the supersede behavior ('A new value SUPERSEDES the old') and the canonical-key semantics, which are important for a write operation. It also communicates the mutable nature. It misses some details (e.g., auth, return value), but the core behavioral trait is covered.

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?

The description is three short sentences, each earning its place: the purpose/verb, the signature with example, and the critical supersede behavior. It is front-loaded with the action word 'Upsert' and wastes no words.

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 simple write operation, the description covers the essential: what it does, how parameters map, and the distinguishing supersede behavior. An output schema exists (per context), so return values need not be documented in the description. It does not discuss usage conditions or prerequisites, but that is not necessary for a low-risk tool with complete parameter documentation.

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?

The input schema already has 100% parameter coverage with clear descriptions. The description adds value by restating the signature in a callable form (record_keyed_fact(subject, attribute, value)) and giving a concrete example that maps the parameters together. This makes the parameter semantics clearer than schema alone.

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 opens with the specific verb 'Upsert' and a clear resource: 'a mutable personal attribute.' It goes on to give the exact function signature with example (user/city/Tampa) and explains the keyed supersede behavior, which distinguishes it from a generic 'record' or sibling tools like record_batch that might append rather than replace.

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 implies usage: call this when updating a mutable personal attribute that should have one canonical value. However, it does not explicitly contrast with alternatives such as record_batch or recall. The inclusion of 'instead of piling up' hints at a distinction but does not name a specific alternative or give when-not-to-use guidance.

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