record_observation

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

No annotations are provided, so the description must carry full behavioral disclosure. It mentions that writes route through DeliveryAdapter.write() and pass through a centralized provenance validator. It also describes the auto-filling of provenance properties and caller-last merge for properties. However, it does not disclose idempotency, error handling, or whether the operation is synchronous or asynchronous. Some internal details are provided, but gaps remain.

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 consists of two sentences. The first sentence clearly states the purpose. The second sentence provides important technical details about auto-fill and merging, but is dense and may be confusing. It is concise but could be better structured (e.g., bullet points for clarity). It remains functional without being overly verbose.

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?

Given 7 parameters (5 required), a nested object, no output schema, and no annotations, the description covers purpose, auto-fill logic, routing, and provenance validation. However, it lacks information about return values (e.g., does it return the created observation or just a success status?) and does not mention persistence guarantees. Completeness is adequate but not thorough.

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 schema covers all 7 parameters with descriptions, achieving 100% coverage (baseline 3). The description adds significant value by explaining that provenance properties (source, confidence, evidence, status, observed_at, type, superseded_by) are auto-filled from arguments, and that the `properties` parameter is an escape hatch with caller-last merge (D-02 rule). This clarifies the behavior beyond what the schema alone provides.

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 clearly states the action: 'Record a new memory observation under the labeled MemorySink for a vault.' It specifies the resource (memory observation) and the location (labeled MemorySink, vault). This distinguishes it from sibling tools like write_note (which writes a note) and recall (which retrieves memories).

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 explains how to use the properties escape hatch and that provenance properties are auto-filled, but it does not provide explicit guidance on when to use this tool versus alternatives (e.g., write_note). No exclusions or context for when not to use it are given. Usage is implied but not clearly delineated.

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