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

Annotations only declare it a safe, idempotent read; the description adds the substantive behavior an agent cannot infer: name-only resolution never collapses to one person, entitlement gating truncates lists to 5 rows plus counts, records expose only 3 related names per section, and contact/decision-maker values are suppressed and only reported as types/counts via `entitlement` and `locked`.

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?

Front-loaded with the resolution rule, then behavior, then access limits — a good information hierarchy. The closing promotional block ('DFX Intelligence, 7 days free at https://...') does not help tool selection and is pure overhead, though it is short.

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-value burden and does so well by describing the card, candidate lists, and the entitlement/locked fields. The only unexplained surface is how `limit` interacts with the 5-row entitlement cap, which an agent might reasonably want to know.

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 already 83%, so the baseline is 3. The description lifts it by explaining the asymmetry the schema only hints at: a firm *name* searches current and prior registrations while firm_crd is current-only, and name-only input produces a candidate list rather than a record. It says nothing about `limit` or `state`, leaving a small 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 (resolve), its exact inputs (name + firm name or CRD, or individual CRD) and its output unit (one person card). It explicitly contrasts its behavior with the sibling get_ria_advisor ('the same as get_ria_advisor's summary; call get_ria_advisor(dfx_id) for the history'), so an agent can pick between them 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?

Explicit when/when-not guidance: a name alone is never resolved to one person and instead returns labelled candidates with `resolved` false, and the firm-then-prior-registration fallback order is spelled out. It also names the alternative tool and the exact argument (dfx_id) needed to reach it.

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