set_extended_property

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

With no annotations provided, the description must carry the behavioral disclosure burden, and it does well by stating that it 'Replaces a same-named property' and that 'Pass the object's table' is required for child object types. It clearly implies mutation and gives a prerequisite, though it omits details about return values, errors, or permissions.

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 at three sentences, each earning its place: the first states the function and types, the second covers object scope and the table requirement, and the third explains replacement behavior and gives an example. There is no redundancy or fluff.

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 absence of annotations and an output schema, the description is remarkably complete for a setter tool. It covers the action, parameter relationships, replacement behavior, and a motivating use case. It doesn't discuss edge cases or return values, but those are less critical for a setter, so the slight omission is acceptable.

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 already covers 86% of parameters, including type defaults and objectType choices. The description reinforces the link between objectType and table and clarifies that value is a JSON string when type=Json, but much of this is already present in the schema. It adds no new meaning for sessionId, so it falls at the baseline.

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 'Set a typed extended property on any model object,' which names a specific action and resource. It then enumerates allowed types (String | Json) and object types (model | table | column | measure | hierarchy | partition), and gives a concrete example (ParameterMetadata tag), making the tool's purpose unmistakable and distinguishing it from siblings like set_annotation.

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 provides clear context by explaining that extended properties are structured metadata and offering a real-world example (ParameterMetadata on field-parameter columns), which implies when the tool is appropriate. However, it does not explicitly compare it to alternative tools or state when not to use it, so it stops short of full explicit guidance.

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