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

Annotations only cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description discloses a rich behavioral profile beyond them: the per-path payload contents, the sub-0.5 confidence labelling of candidate links, and an unusually detailed entitlement model (5 free rows, locked.count/by_type, contact values withheld, disclosure mirrored in `entitlement`/`locked`). This is exactly the kind of context the agent needs before calling.

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?

Densely front-loaded: purpose first, then path payload, then epistemics, then access. Nearly every clause is load-bearing given the tool's complexity, though the closing promotional line ('7 days free at ...') is sales copy rather than invocation guidance.

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 and a fairly complex, multi-sectional return, the description carries the burden well by describing what each path contains, how confidence works, and what entitlement/locked will report. An agent can predict both the payload shape and its truncation behavior.

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 67% and the dfx_id enumeration is already fully documented in the schema itself. The description adds nothing about `kind` naming conventions or `limit` interaction with the lock behavior, so it neither compensates for the coverage gap nor repeats the schema usefully.

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: 'Published capital flow paths through one institution', then enumerates the three concrete shapes (allocator→manager, lender→borrower, properties under a RE manager). It is far more specific than a name restatement, but it never differentiates itself from the closest sibling, `relationship_path`, which also returns graph paths.

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 strong interpretive guidance (NOT_COVERED means not computed, not 'no relationship'; paths built only from identity-grade or measured links), which implicitly frames when the result is trustworthy. However, it offers no explicit when-to-use versus `relationship_path` or the various `find_*` tools, and no stated prerequisites beyond the paywall note.

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