link_query

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

The description provides useful behavioral context: edges are extracted automatically via zero-LLM regex from task memos and reports, and it lists the types of IDs supported (wf_id, uuid, short-hash, memory-slug). However, since no annotations are provided, the description should ideally disclose more about side effects or performance, such as whether the tool is read-only or if it triggers any background processing. The given info is adequate but not exhaustive.

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 concise and well-structured: two sentences front-loading the core purpose followed by a succinct explanation of edge extraction and supported ID types. Every sentence adds essential information without redundancy.

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 moderate complexity (4 parameters, 100% schema coverage, and an output schema), the description is mostly complete. It explains the source of edges and the kinds of endpoints, which is sufficient for most use cases. However, it could mention that results are paginated via the limit parameter or that direction defaults to both, but these are inferred from the schema. The output schema likely provides return structure, so the description is adequate.

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?

Input schema coverage is 100%, so the schema documents all four parameters well. The description adds value by clarifying that edges are derived from specific sources (task memos and reports) and by explaining the endpoint kinds more explicitly than the schema's descriptions. It also gives concrete examples of ID formats, which enhances understanding beyond the schema's generic descriptions.

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 queries cross-domain reference edges for an object, specifying both inbound and outbound directions. The verb 'query' and resource 'cross-domain reference edges' are specific, and the tool distinguishes itself from siblings like 'link_trace' and 'unified_search' by focusing on automatically extracted edges.

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 explains when to use the tool: to find references to or from an object. It also specifies that edges are extracted automatically from task memos and reports, setting context for appropriate usage. However, it does not explicitly state when not to use it or compare directly to siblings like 'link_trace' or 'unified_search', which may have overlapping functionality.

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