extract_subnetwork

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context by disclosing that the response contains a subnetwork_id, an input status, and at most 30 preview edges, with full edges reserved for export. That truncation behavior is exactly what an agent needs before deciding whether to chain a second call. It does not explain the refresh/max_edges interaction or whether the returned subnetwork_id persists server-side.

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 front-loaded sentence: action, then return shape, then export caveat. No filler, no restatement of the tool name.

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?

Reduced to 4: with an output schema present, return values need not be explained, yet the description spends most of its length on them while leaving all five inputs undocumented at 0% schema coverage. For a tool with two enum choices and a caching flag, an agent is left guessing about required inputs.

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 0% across five parameters, so the description carries the full burden and largely fails: it only alludes to symbols ('输入名称集合'). Nothing explains species, the core vs complete dataset enum, refresh, or max_edges (capped at 5000), nor why the preview cap is 30 when max_edges defaults to 5000 — a genuine ambiguity left unresolved.

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?

States a specific verb and resource: extracts the directed network induced by a set of input names. It also distinguishes itself from the export path by noting the result is a capped preview, so an agent can tell it apart from export_network without opening the schema. It stops short of naming sibling tools explicitly.

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: call this when you have a set of entity names and want the internal subnetwork. The clause '完整边用于导出' hints that full edges require a follow-up export, which is a partial routing cue, but there is no explicit when-to-use vs when-not versus summarize_network, get_neighbors, or search_interactions.

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