list_objects

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

With no annotations, the description carries the full burden and does disclose a non-obvious behavioral trait: objects that a human marked as wrong are excluded by default and surfaced separately in left_out, with include_wrong=true returning everything. It also sketches the returned payload, which matters since no output schema exists. Remaining gaps are pagination/ordering and whether left_out is a top-level key or inline.

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 compact clauses with the payload contents up front and the filtering rule second, so the most decision-relevant behavior is reachable quickly. The field enumeration ('人的判断', '几条关系') is terse to the point of ambiguity, but nothing is filler.

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 list tool with no annotations and no output schema, the description covers what is returned, what is default-filtered, and how to override it. What is missing is modest: whether results are paginated or ordered, and the exact meaning of the human-judgment flag values.

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 saved_as and include_wrong are already documented, and the description mostly restates include_wrong ('全给') while adding the left_out consequence. That added consequence is genuinely useful but does not go much beyond the schema, so the baseline 3 is right.

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 (objects in the ontology) and enumerates exactly what each listed object carries: name, description, source tables, identifying fields, record count, relation count, and human judgment. That makes the listing distinct from list_questions/list_rules/list_relations even without naming a sibling, though the verb itself ('list') is only implied by the enumeration.

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?

Usage is implied rather than stated: you call it when you need an overview of the objects in an ontology, and include_wrong controls whether human-rejected objects appear. There is no explicit guidance on when to prefer this over object_fields, object_rows, or list_relations, and no prerequisites beyond the saved_as requirement inherited from the schema.

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