record_observation

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

With no annotations provided, the description must disclose behavioral traits. It states that all writes are attributed to the operator or agent, and explains that corrections separate entities on the next rebuild. However, it does not explicitly state that the operation mutates state, nor does it mention failure modes, permissions, or idempotency, leaving room for improvement.

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 compact and front-loaded with the core purpose, then provides the kind list, the special correction usage, and the attribution rule. It is efficient, though the long list of kinds makes it dense; every sentence serves a purpose.

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?

As a write operation with five parameters, the description covers the main use and the notable correction case, but does not explain the remaining parameters (fact_type, segment_ids, engagement beyond its schema description) or the success/failure behavior. This leaves agents without full information for correct invocation in all scenarios.

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 low at 20%, so the description should compensate. It does clarify the 'kind' parameter by listing its allowed values and explains the special 'data' structure for corrections. However, it leaves 'fact_type', 'segment_ids', and the general shape of 'data' unexplained, which the schema also does not describe.

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 a precise statement of the tool's action: recording operator observations not present in captured terminal output. It enumerates concrete example kinds and a full list of allowed values, and it is clearly distinct from the sibling read/list/search tools.

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 specifies when to use the tool: for capturing information that is not in captured terminal output. It also provides explicit usage for the special correction case. However, it does not directly name alternative tools for situations where the information is already captured, relying on inference from the tool name and siblings.

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