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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds one valuable nuance: 'without treating missing edges as false,' which distinguishes absent data from negative facts. However, it fails to disclose basic behaviors such as whether the operation is read-only, what the return structure looks like (nodes, edges, facts), or what happens if the entity is not resolvable. The 'bounded' qualifier implies limits but doesn't explain the effect of depth on response shape.

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 a single sentence with no filler, front-loading the core action. It is concise and each word contributes meaning. However, it is so terse that it borders on under-specification for a complex tool with 13 parameters, making it slightly less effective than a slightly expanded version that could clarified the return format and prerequisites.

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 complex traversal tool with no output schema and no annotations, this description is incomplete. It does not explain what the response contains (e.g., nodes, edges, facts, expansion blocks), how depth affects the output, or error behavior when entity is missing or unresolved. The prerequisite that an entity is required is only buried in the schema's depth description, not the main description. The description leaves too much unsaid for an agent to invoke it confidently on complex tasks.

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 high (85%), so the baseline is 3. The description adds minimal semantic value beyond the schema—it references 'bounded' and 'typed' which map to depth/limit/type, and 'missing edges' relates to truthStates, but it does not elaborate on individual parameters. The schema itself already documents most parameters well, so the description doesn't need to compensate significantly.

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 core action: 'Traverse bounded, typed economic relationships from a resolved entity.' It specifies a verb ('traverse'), a resource ('economic relationships'), and key qualifiers ('bounded', 'typed') that hint at the depth/limit/type parameters. It distinguishes itself from general search tools like search_entities or query_knowledge_graph by focusing on relationship traversal from a single resolved entity, though it does not explicitly name an alternative.

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 gives no explicit guidance on when to use this tool versus sibling tools like find_connected_entities or resolve_entities. The phrase 'from a resolved entity' implies a prerequisite (use resolve_entity first), but it is not stated explicitly. There is no mention of when this tool is preferred over a general graph query or other traversal-like tools.

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