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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the real burden is on the description — and it delivers: it discloses entitlement gating (first 5 rows plus locked.count/locked.by_type under a free plan), redaction rules (contact values and decision-maker names reduced to types and counts), and the `entitlement`/`locked` envelope in every answer. This is behavioral detail an agent cannot get from the annotations or schema.

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 purpose is front-loaded and the ACCESS block is labeled clearly, but the run-on entitlement sentences pack in a lot of clause-level detail and the closing sales pitch ('7 days free at https://dfxintel.com/data-factory/plans') does not earn its place in a tool definition. Trimmed, the behavioral content would still survive intact.

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?

With no output schema, the description carries the return-shape burden and handles it well, naming the fields per edge (role, dates, currency, confidence, evidence class, source) and the redaction/locking envelope. What is missing is pagination and limit behavior, and the interaction between limit and the 5-row entitlement cap.

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 coverage is only 40%: dfx_id and detail are self-documented, but limit, rel_type, and current_only appear nowhere in the description. The enumeration of edge types gives indirect hints about rel_type values, but nothing explains limit semantics, whether current_only filters by end-date, or the default filtering behavior — so the description fails to compensate for the coverage 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 and resource — 'Every published relationship touching one entity' — and enumerates the edge types returned (EMPLOYS, PRINCIPAL_OF, INVESTED_IN, etc.) plus same_as cross-graph links. That is enough for an agent to distinguish it from get_entity (attributes) and relationship_path (traversal) without opening a schema.

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 'touching one entity' and the required dfx_id, but there is no explicit when-to-use, no when-not-to, and no named alternative (relationship_path or get_entity are obvious siblings that go unmentioned). The long ACCESS paragraph describes consequences, not selection guidance.

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