get_property

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

No annotations are provided, so the description carries the transparency burden. It explicitly notes that 'an unknown property name raises rather than returning junk,' which is a key behavioral detail. However, it does not mention whether the operation is purely read-only, though the verb 'read' implies that.

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?

Two concise sentences with no filler. Every word adds meaning, and the key behavioral note is included without redundancy.

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 single-property read, the description covers the essential behavior (raising on unknown names). It lacks explicit details about return types or error conditions beyond the note, but given the simplicity of the operation, it is reasonably complete.

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 provides no descriptions for 'ref' or 'name', and the description does not explain them. While 'ref' as an object reference and 'name' as a property name are inferable, the lack of explicit definition leaves ambiguity—especially for 'ref,' which could refer to different kinds of references.

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 tool's function: 'Read one property of an object.' It distinguishes from siblings like set_property (mutation) and inspect_object (likely whole-object inspection) by focusing on a single read.

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 when to use this tool—when you need one property of an object—but it does not explicitly contrast with alternatives like inspect_object or mention when a different tool would be preferred. The guidance is minimal but sufficient for the simple case.

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