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

Annotations already declare a safe read (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: depth bounds 1–3, a 100-node cap, explicit truncation signalling on clipped networks, exclusion of individuals, credit cost, and the fact that an unpublished root is free. These are exactly the operational facts an agent cannot infer from structured fields.

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?

Telegraphic and front-loaded: purpose first, then access constraint, then operational limits, then caveats and cost — every clause carries information and none is redundant. The 'Costs 15 credits (15p)' phrasing is slightly compressed but still parseable.

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 graph-traversal tool with an output schema, the description covers the decisions an agent must make — auth, depth, node cap, truncation interpretation, cost, and the trap of reading absent links as negatives. The remaining hole is the meaning and output shape of each 'kind' value, which the schema leaves undocumented.

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 carries the burden and only partly meets it: it bounds 'depth' to 1–3 and implies the 100-node ceiling that binds 'limit'. It says nothing about the seven enum values of 'kind' (organizations, titles, agents, properties, buildings, land, listings) or the expected form of 'entity_id', which are the two required parameters.

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 ('Investigate') and resource scope ('recorded corporate ownership, title and agency relationships'), which is far more than a restatement of the name. It does not, however, distinguish itself from close siblings such as actor_path or entity_relationships, so an agent must infer the split.

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?

Gives a hard usage constraint ('Requires the customer's account; never use an anonymous preview key') and implicit scope limits ('Individuals are excluded'), which is genuine when-not guidance. It never names an alternative tool or explains when to prefer a path/reachability lookup over a network expansion, leaving the sibling choice to inference.

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