resolve_kg

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

With no annotations provided, the description carries the full behavioral disclosure. It explicitly states the tool is '确定性只读' (deterministic read-only). It explains the leaf detection nuance (use is_leaf not level) and return format. It does not mention rate limits or auth requirements, but for a read-only tool, the transparency is good.

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 detailed but well-structured with sections and bullet points. It is not overly verbose; each part adds value. However, it could be slightly more concise, e.g., by reducing the redundancy of the leaf depth explanation. Overall, it balances detail with readability.

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 tool's complexity (6 params, one required) and no formal output schema, the description covers all necessary aspects: purpose, parameter usage, behavioral notes, return format, and edge cases (no matches return count=0 without error). It also provides a workflow context for downstream tools (ingest_items). This is comprehensive.

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?

Despite 0% schema description coverage, the description adds substantial meaning to all 6 parameters. It provides example values for subject_root (e.g., '100' for Math Grade 7), explains the effect of parent_id overriding subject_root, and clarifies the use of leaves_only. This goes well beyond the schema's basic types and defaults.

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 purpose: 'KG 锚定查表（确定性只读，数学+科学一套通吃）' indicating it is a read-only lookup in a knowledge graph for math and science. It specifies the actions: query by name, section number, or parent node under a textbook root. While it does not explicitly differentiate from sibling 'list_kg_tree', the description implies this tool is for targeted anchored lookup, not tree exploration.

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 a clear workflow: first use query fuzzy to find candidates, then pick a leaf node (is_leaf=true) as kp_id for ingest_items. It also covers exact match by section_num for exercise papers. However, it lacks explicit 'when not to use' or comparison to alternatives like list_kg_tree, slightly reducing the score from 5.

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