observation_create

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal one important trait: it will never auto-promote to invariant/decision. However, it omits other potentially relevant behaviors such as whether the operation is reversible, any permission requirements, or side effects beyond creation. For a create operation, the mutation is implicit, but additional context about what happens on success or failure is absent.

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 extremely concise, using just two sentences with no filler. It front-loads the core purpose and includes the important behavioral caveat. However, it is so brief that it sacrifices necessary detail, so while it is efficient, it is under-specified. The structure is clear and scannable.

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 the tool's complexity (8 parameters, 4 required), 0% schema coverage, and no annotations, the description is severely incomplete. It fails to explain what an observation memory is, how the parameters relate, or any constraints. The output schema exists but doesn't compensate for the lack of input guidance. An agent would struggle to call this tool correctly without external knowledge.

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 0%, so the description must compensate by explaining parameter meanings, but it provides none. The 8 parameters (especially 'statement' vs 'observation', 'context', 'details', 'project', 'confidence') are entirely undocumented. An agent receives no help in distinguishing these fields or understanding required formats. This is a critical gap.

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 states a specific verb ('Create') and resource ('observation memory'), which clearly defines the tool's primary function. It distinguishes from sibling tools by naming the memory type, though it doesn't explicitly contrast with alternatives. The 'Never auto-promote' clause adds a nuance but doesn't detract from clarity.

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?

There is no explicit guidance on when to use this tool versus the many sibling creation tools (e.g., assumption_create, decision_create). The description implies its use for observation memories, but provides no criteria for selection, no exclusions, and no context about when an observation is appropriate vs. other types. The 'Never auto-promote' is a behavioral rule, not usage guidance.

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