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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: entitlement gating (first 5 rows plus locked.count/locked.by_type), permanent withholding of contact values and decision-maker names, the 2011-onward ADV coverage window, and the rule that absence is not evidence of no commitment. It also heads off misreads (a commitment is the plan's number, not fund size; gross asset value is not fund size).

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?

Information density is high and the return fields are front-loaded before the caveats and access rules, so nothing critical is buried. It is long and the opening sentence is an unwieldy run-on, and the closing '7 days free' plan pitch is promotional filler that does not help an agent invoke the tool.

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 a 15-parameter, no-output-schema tool, the description covers what the rows contain, how entitlement truncates results, what is always withheld, and the data provenance/coverage caveats. An agent has enough to call it correctly and to interpret an empty result without over-reading 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?

At 60% schema coverage with 15 params, the description earns its keep by mapping filters to meaning (manager dfx id or CRD, vehicle, allocator, name, state, commitment type, private-real-estate-only, min amount, since) and by clarifying similar_to and group_by semantics. It leaves sort, limit and cursor behavior to the schema, which is a minor gap rather than a failure.

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 names a specific resource (the public LP tape of commitments to real estate fund managers and vehicles) and enumerates exactly what each row carries (plan, manager/vehicle, fund, commitment amount with basis, dates, paid-in/distributed/value/IRR). The 'real estate fund' scope cleanly separates it from siblings like search_vc_lp_commitments and search_allocator_commitments without ambiguity.

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?

It gives concrete usage context: 'similar_to=<manager>' is framed as the answer to 'which LPs back managers like X', and group_by=allocator is explained as rolling rows up per plan. The filter list tells the agent what selective dimensions exist, but it never explicitly states when to choose this tool over a sibling like search_allocator_commitments or get_commitments.

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