object_fields

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

With no annotations supplied, the description carries the full burden, but it partially meets it by disclosing the content of the response (types, lengths, nullability, source tables), which substitutes for an absent output schema. It says nothing about whether the call is read-only, what happens when the object key is invalid, or whether the result is empty for unprofiled objects.

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?

A single sentence with a front-loaded subject, followed by a parenthetical that gives the business rationale for the source-table column. No redundancy beyond what the parenthetical is worth.

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 two-parameter, non-destructive read tool with full schema coverage, the description covers what is returned well enough. It remains thin on selection mechanics (which object, which run) and on the notion of 'failure', even though the schema covers those parameters.

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 100%, so both parameters are already documented; the baseline of 3 applies. The description adds the meaningful nuance that each field's source table is the column to fill in when handing the dataset to the data platform, but it never mentions either the type or the saved_as parameter by name or meaning.

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 names the resource (一个对象的属性 — an object's field attributes) and enumerates what each field reports (type, length, nullability, source table), so the agent knows it yields a schema-like listing. But there is no verb and no explicit contrast with the adjacent object_rows tool, which appears to return data rather than field metadata.

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?

No when-to-use statement, no prerequisites, and no alternative named. The reader is not told, for instance, that list_objects must be called first to obtain the object key, nor when object_fields is preferable to object_rows, ask_question, or data_layout.

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