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

Annotations already cover read-only/idempotent/non-destructive, yet the description goes further and discloses the actual access model: unpaid vertical returns the first 5 rows in full plus locked.count/locked.by_type and never the rows; contact values and decision-maker names are never returned; withholding is reported in `entitlement` and `locked`. This is exactly the kind of non-obvious behavioral context the annotations cannot express.

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?

Dense but disciplined: the object shape, then the filters, then usage examples, then access limits — each block earns its place. The closing promotional line ('7 days free at https://dfxintel.com/data-factory/plans') is the one sentence that is marketing rather than operational guidance.

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 13-parameter, no-output-schema, low-coverage tool, the description supplies the return shape (counts first, locked.count/by_type, entitlement) and the withholding rules, which is the hard part. It omits semantics for a handful of lesser parameters (limit, within_days, geography, type vs types), so it is strong but not airtight.

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 15%, so the description carries most of the burden and does so for the important filters: it enumerates all provider_type and persona values, names the five family values, explains provider_gap, and clarifies that state/city nest (metro holds its cities) and that sector is word-based. It leaves limit, within_days, geography, and the type/types distinction unexplained, so it is not fully compensating.

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 the resource (venture opportunity object), enumerates the five signal families and the full filter vocabulary, so an agent knows exactly what is being searched and over what fields. It stops short of explicitly distinguishing itself from near-neighbors such as search_vc_service_opportunities, search_opportunities or search_forward_opportunities, which is the only thing keeping it from a 5.

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 three concrete usage examples ('opportunities for a venture law firm in Boston', 'what should I look at this week as a seed investor', 'new funds with no auditor on record') plus the rule that 'a metro holds its cities', which is real selection guidance. It never states when NOT to use this tool or which sibling to prefer instead, so it is clear context without exclusions.

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