Add Observations

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

Annotations already indicate it's a write operation and non-idempotent; the description adds the crucial failure behavior when the entity does not exist and clarifies that observations are atomic facts. This goes beyond what the annotations convey about side effects.

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 entire description is a single 19-word sentence that front-loads the primary action and includes a key constraint. No redundant phrases or filler; every word earns its place.

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 with annotations and a schema, the description provides the essential context: purpose, target, and a crucial error condition. It doesn't discuss return values, but the presence of an output schema covers that, and behavioral annotations handle idempotency and safety.

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 documents the namespace, entityName, and contents parameters with descriptions, but the top-level observations property lacks a description. The tool description compensates by explaining observations as atomic facts and emphasizing that entityName must refer to an existing entity, adding semantic meaning to the parameters.

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 identifies the action (add), the resource (observations as atomic facts), and the target (existing entities in the knowledge graph). It distinguishes itself from sibling tools like create_entities and create_relations by specifying the verb-noun combination and the constraint that entities must exist.

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 context, such as the need for entities to already exist, but does not explicitly state when to use this tool versus alternatives like create_entities or delete_observations. The failure condition suggests a prerequisite but no direct comparison to siblings.

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