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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavioral context the annotations cannot: the paywall behavior (5 full rows plus locked.count/locked.by_type), per-record truncation to first 3 related names, permanent omission of contact values and decision-maker names, and the `entitlement`/`locked` report. This is exactly the kind of disclosure that changes how an agent frames results to a user.

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-loads the resource and returned fields, then filters, then access caveats — a logical order with almost no filler. The closing plan-promotion sentence plus URL is the only slightly promotional element, but it is attached to a genuine entitlement caveat rather than being pure marketing.

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 still explains both what a list returns (rows plus locked counts) and what a record returns, including the withholding markers in `entitlement` and `locked`. For an 8-parameter, zero-required search tool this covers everything an agent needs to call and interpret it.

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?

The description enumerates the filter set (office, sector, asset class, state, kind, since-date) which maps to six of the eight parameters, but it adds no syntax or value guidance beyond the schema, and `limit` and `include_candidates` are absent from the description. With 63% schema description coverage, the schema carries most of the meaning, so a baseline 3 is appropriate.

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?

Opens with a concrete verb+resource: 'Dated investments family offices have been observed making,' then enumerates the exact fields returned (target, sector, asset class, structure, control/minority, board seats, exits, source quote). The 'family offices' subject cleanly separates it from sibling searches like search_vc_investments, search_pe_transactions and search_family_offices, so an agent can route to it 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?

Gives a clear use case ('The evidence behind "this office backs X"') and lists the filter dimensions, which tells the agent when the tool applies. It stops short of naming alternatives or stating when NOT to use it (e.g. to find offices themselves use search_family_offices), so it is clear but not fully disambiguating.

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