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

Annotations already cover the safe-read profile (readOnlyHint, idempotentHint, non-destructive), and the description adds substantial context beyond them: the entitlement model (first 5 rows in full plus locked.count/locked.by_type, never the rows), the redaction rules (contact values and decision-maker names withheld, only types/counts returned), and the guarantee that every answer carries `entitlement` and `locked`. That is exactly the kind of output-shape and withholding disclosure an agent needs to interpret results correctly.

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 definition is front-loaded with the returned fields and filters before the long access/entitlement paragraph, so the core purpose lands first. It is dense but nearly every clause earns its place, with the only marginal cost being the trailing '7 days free at https://...' upsell line.

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 does the heavy lifting by specifying the returned amount fields and the shape of locking (`locked.count`, `locked.by_type`, `entitlement`), which is the hardest thing for the agent to guess. Gaps remain around pagination/limit behavior and sort semantics for a 10-parameter tool, but the return-value and withholding story is well covered.

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 30%, so the description must carry weight: it clarifies strategy, vintage range (min/max_vintage), lifecycle, and Form D sold, adding real meaning for the amount/lifecycle filters. It stays silent on sort, limit, query, fundraising_state (distinct from lifecycle), and organization_dfx_id, so roughly half the parameters remain undocumented, which is a partial rather than full compensation for the coverage 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?

The description states a specific resource (venture funds) and enumerates the exact amount fields returned under each fund's name (target, first close, final close, announced size, Form D offering/sold, ADV gross asset value), which is concrete enough to separate it from search_vc_firms or search_vc_new_funds. It stops short of naming any sibling explicitly, so an agent must still infer the boundary rather than being routed.

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?

The sentence 'Filter by manager, lifecycle, vintage range, strategy or Form D sold' implicitly signals the query shapes this tool answers, which is useful implied usage. However, with many near-neighbor searches (search_vc_firms, search_vc_new_funds, search_vc_lp_commitments) there is no explicit when-to-use, when-not, or alternative routing, which is where the definition leaves the agent on its own.

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