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

Annotations only declare the standard read-only/idempotent profile, and the description goes well beyond them: it discloses exactly what is withheld without a paid plan (first 5 rows in full, remainder only as locked.count/locked.by_type, never the rows), that contact values and decision-maker names are never returned, and that every response announces its restrictions in `entitlement` and `locked`. That is precisely the behavioral context annotations cannot carry.

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 what/where before the access caveats, and the entitlement paragraph is dense but earns its place for a data-licensing tool. The closing promotional URL sentence is slightly out of register, but overall the structure is sound and waste is minimal.

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?

No output schema exists, yet the description covers the return shape well ('Compact cards with stable dfx ids and a per-domain coverage note') plus the entitlement/locked fields, so an agent knows what comes back. The main residual gap is the parameter surface, which is more of a parameter-semantics issue.

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 only 21% across 19 parameters, so the description carries the burden. It names entity_type, domain, state, sector and implies '...' more, but the bulk of filters (city, stage, vertical, active_only, asset_class, min_aum_usd, min_opportunity, invests_directly, recent_activity_days, has_sponsor_relationships, sort, cursor) remain undocumented in both places, leaving an agent guessing at boolean/range semantics.

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+resource ('One search across family offices, independent sponsors... private companies, venture firms, PE firms and funds, and real estate organisations') and explicitly positions itself against the sibling domain searches ('fewer per-domain filters than the domain searches'). An agent can immediately tell this is the cross-domain meta-search distinct from search_vc_firms, search_pe_firms, etc.

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 clear context: use for breadth across every domain in one query, at the cost of fewer per-domain filters — which routes the agent toward the domain-specific siblings when deep filtering is needed. It stops short of naming specific alternatives or stating explicit when-not conditions, so it is a 4 rather than a 5.

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