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

Beyond the annotations (which already declare a safe read-only, idempotent operation), the description adds real behavioral context: bounded and eventually consistent results, the caveat that missing links do not imply absence/ownership/off-market status, that no private ownership payloads are returned, and that calls are free. It stops short of describing traversal cost at higher depth 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?

Five short, telegraphic sentences that are front-loaded with the purpose statement and each carry distinct information (routing, provenance, consistency caveats, payload limits, cost). No filler, though the clipped style makes a few claims (e.g. 'derived graph') harder to parse than an explicit sentence would.

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?

An output schema exists, so return format needn't be covered, and the annotations carry the safety profile. The description usefully adds consistency and provenance caveats, but for a traversal tool with 0% parameter documentation it leaves depth/limit semantics and the choice against sibling traversal tools unaddressed, so an agent still lacks enough to call it confidently.

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 carry parameter meaning, and it only partially does: it clarifies entity_id semantics ('canonical ids from search') and hints that results are bounded (relevant to depth/limit). The meaning of 'depth' (default 1, presumably traversal hops) and 'limit' (default 25, presumably max results) is never explained, which are the two parameters that most affect how the tool is invoked.

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 states the resource ('relationship evidence from the derived graph'), which maps to a relationship-traversal tool, but it never says plainly what the tool returns or does — e.g. 'returns entities related to entity_id of a given kind up to depth'. It also does not differentiate itself from siblings like actor_network, actor_path, ownership_by_company or lookup_entities, so an agent must infer the distinction.

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?

'Use canonical ids from search' is an implicit prerequisite routing the agent to the entity-search siblings, and 'Cite path provenance and publication dates' hints at how results should be used. However, there is no explicit when-to-use/when-not versus the numerous relationship-adjacent siblings, leaving selection largely to inference.

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