expand_links_network

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

With no annotations, the description carries the full burden and does reasonably well: it declares 'Read-only', discloses hard constraints (max_depth capped at 3, node/edge/fan-out caps), and warns that truncation flags are returned. It omits auth/permission requirements and any rate-limit or pagination behavior.

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?

Dense but front-loaded: purpose, then parameters, then return shape, then safety. No wasted sentences, though the parameter run-on is packed tightly enough to risk being skimmable.

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 13-parameter BFS graph tool, the description covers the semantics an agent needs to bound the traversal and interpret return values (an output schema exists, so return details need not be exhaustive). The unaddressed include_raw/include_node_summaries flags and absent auth notes are the remaining shortfalls.

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%, so the description must compensate, and it does for most parameters: direction values, the depth cap, the node/edge/fan-out caps, and the allowed_types/category_ids/status_ids/title_regex filters are all explained with their JSON-array/pattern format. It leaves include_raw, include_node_summaries, root_type, and root_id unexplained, which is a real but partial gap.

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 ('Build the directed link graph') and resource, plus the algorithm (BFS) and scope (around a root experiment/item). This clearly distinguishes it from the sibling get_entity_links, though the sibling is never named 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 by 'around a root experiment/item via BFS' – an agent can infer this is for multi-hop traversal. However, it never says when to use this versus get_entity_links or get_item, and gives no exclusions or prerequisites.

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