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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is known. The description adds real value by listing the returned fields, stating the no-employee-search boundary, and flagging a payment-chain restriction (Base or Polygon only, not Solana). It does not cover result variability, rate limits, or why the call is non-idempotent, which would matter for a live web search.

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 four short sentences, front-loaded with the core purpose and followed by return fields, next step, and constraints, with no filler. The payment-chain sentence ('Not offered on Solana...') is operationally necessary but sits awkwardly inside a tool-purpose description.

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, the description usefully compensates by enumerating return fields (names, URLs, industries, location, search summaries). For a five-parameter read-only search, the main remaining gap is what happens on empty or partial matches and how many results typically come 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 100%, including enum values for size and the clamping behavior of limit, so the schema already carries the parameter detail. The description only restates that location, industry, and size are optional filters and adds no semantics beyond that — notably it does not explain that industry expects a LinkedIn industry ID rather than a name.

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 verb and resource ('Find LinkedIn companies by keywords') and enumerates the filter dimensions (location, industry, company size). It implicitly distinguishes itself from the enrichment sibling by noting 'Use the returned URLs with company enrichment for further research', though it never names that tool explicitly, so an agent must infer that linkedin-company is the enrichment step.

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 clear context for when to reach for this tool (keyword discovery with optional filters) and states an explicit exclusion ('No employee search is performed'). The follow-up step to enrichment is a useful hand-off, but there is no explicit when-not-to-use guidance for this tool versus linkedin-company or the generic linkedin sibling.

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