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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it details the entitlement-gating behavior (first 5 rows in full, counts only for the rest via locked.count/locked.by_type), that contact values and decision-maker names are never returned, and that every answer reports what it withheld in `entitlement`/`locked`. It also pre-empts misuse with 'Never a prediction'.

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 the rule and use cases, then separates ACCESS details. Efficient overall, though the final promotional line with a pricing URL is marketing rather than task-relevant 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 tool with no output schema and no annotations covering data-return behavior, the description fills the gap: it defines the candidate rule, the filter axes, and the exact response shape under both entitled and locked states, so an agent knows what it will and won't get back.

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 13% (just `state`), so the description must compensate. It does explain the semantics of the months-since window and the filter dimensions (sector, state/city, stage, window), but leaves `geography`, `limit`, and the interaction between the min/max month bounds unexplained. Partial compensation only.

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 verb and resource (search venture-backed companies) plus the exact inclusion rule: last dated financing 12-36 months ago, no exit, still on a DFX-read portfolio page. This sharply distinguishes it from siblings like search_vc_financings (raw financings) and search_vc_next_funds, and the title's 'candidates by rule' framing is reinforced in the body.

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 explicit use-case phrasings ('portfolio companies that may raise in the next 12 months', 'companies due for their next round') and enumerates the filterable dimensions. It stops short of naming which sibling tool to use instead when the user wants raw financings or a predictive signal, so no explicit alternatives/exclusions.

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