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

The description adds minimal behavioral context by indicating that a custom question is used, which suggests an AI/research operation. However, it does not disclose side effects, caching, credit consumption, asynchronous processing, or output characteristics. Annotations (readOnlyHint:false, openWorldHint:true) provide some safety signals, but the description itself offers very little beyond the phrase 'custom question'.

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 description is a single sentence with no wasted words, and it front-loads the core differentiator ('custom question'). It is concise and easy to parse, though it sacrifices depth for brevity.

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?

Given the complexity of the tool (huge schema, no output schema, many options for answerType, templates, webhooks, verification), the description is insufficient. It fails to explain what an enrichment returns, whether results are cached, or how to choose this over standard enrichment tools. The extensive schema documentation prevents a score of 1, but the top-level operational context is largely missing.

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?

The input schema provides rich descriptions for all parameters, including examples, defaults, and detailed explanations for webhook, forceRefresh, outputSchema, and verificationMode. The tool description itself adds no parameter-level meaning beyond the general 'custom question' context, so the schema carries the full burden and the baseline 3 is appropriate.

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 uses a specific verb ('Enrich') and identifies the resource ('a company') plus the distinguishing mode ('custom question'), which differentiates it from sibling tools like companies-enrich_firmographics or companies-enrich_funding. However, it does not state what enrichment produces or how it relates to signals/templates, so it's not 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?

The phrase 'custom question' weakly implies this tool is intended for ad-hoc research questions rather than predefined enrichment types, but it gives no explicit when-to-use or alternative guidance. There is no mention of batch variants, template usage, or when to prefer standard enrichment tools, so it only reaches an implied level.

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