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

Goes far beyond the readOnly/idempotent annotations by disclosing the entitlement gating model (first 5 rows plus locked.count and locked.by_type, never full rows), the fields every answer carries (entitlement, locked), the data never returned (contact values, decision-maker names), and the 90-day lifecycle rule for held deals. This is exactly the behavioral context annotations cannot convey.

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 useful content (types, then record fields, then access rules), but the single dense block mixes many concerns and ends with a promotional line about paid plans and a signup URL that does little for an agent. Information-dense yet somewhat overpacked.

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 and complex entitlement logic, the description covers row structure, withheld data, and the entitlement/locked reporting model well, which is what an agent needs. It stops short of fully documenting the filter parameters (limit, since, state, persona) that shape results.

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 33%, so the description must compensate. It adds real meaning for opportunity_type (enumerating all six values) and status (held behavior, 90-day rule), but says nothing about limit, since, state, or persona beyond what the thin schema already states. Partial compensation for a low-coverage schema.

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 (ISI opportunities in the shared opportunity contract, rule isi-opp-1) and enumerates the six opportunity types, so an agent knows precisely what domain this covers. It differentiates from generic siblings somewhat via the ISI contract naming, but never explicitly contrasts with search_opportunities or search_forward_opportunities.

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?

Provides conditional guidance that the three HELD types are returned only with status=held, and explains what happens without a paid plan. However, it never states when to choose this over sibling tools like search_opportunities or find_opportunities_for_capital, leaving tool selection to inference.

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