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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses exactly what a free tier withholds (first 5 rows, locked.count and locked.by_type, no contact values or decision-maker names), how records are truncated per section, and that every response carries `entitlement` and `locked`. This is unusually rich disclosure of a non-obvious access constraint.

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 first two sentences are well front-loaded and dense with useful meaning, but the entitlement paragraph is long and ends with a promotional plan URL that reads as marketing rather than tool guidance. The access rules earn their place; the sales link and some redundancy ('never returned, only their types and counts') do not.

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?

For an 11-parameter, no-output-schema tool this covers the critical ground: what a row contains, what filtering is possible, and the entitlement/locked response contract. The main gap is that several parameters (limit, within_days, all_vehicles, lifecycle_state) are never explained in prose, so an agent must infer their effect.

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 18%, so the description must compensate and largely does: it explains `since` (first Form D/ADV appearance), `raising_now` (open Form D offering), `emerging_only`, state/city, sector, and explicitly defines `max_fund_number=2` as 'Fund I and II'. It leaves `limit`, `within_days`, `all_vehicles`, and the `lifecycle_state` enum semantics unaddressed.

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 resource and two distinct retrieval modes ('launched since a date (first Form D sale or first Form ADV appearance)' or 'open Form D offering'), plus the row grain ('one row per manager') and the fields returned. An agent can distinguish this from search_vc_funds, search_vc_next_funds, or search_vc_emerging_managers from the text alone.

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 concrete invocation triggers ('funds raising now', 'managers that launched a new vehicle in the last 90 days', 'new venture funds likely needing an administrator'), which is strong context. It never names a sibling tool or states when NOT to use this one, so it stops short of the 5-level bar.

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