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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the 'loaded curated' scope and the demo-mode limitation, which are useful but thin. No contradiction exists between the description and annotations.

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?

Two sentences with no filler; the core search behavior and searchable fields are front-loaded, and the demo-mode note adds context without bloating the 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?

For a one-parameter read-only search tool, the description covers the query semantics and the curated nature of the dataset. It lacks any mention of result limits, response shape, or how to use demo mode, but the absence of an output schema and the tool's simplicity keep the gap modest.

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 schema only describes q as a generic string with a 'technology' example, giving little semantic guidance. The description compensates by specifying that q may be a name, domain, industry, or ticker, meaningfully enriching the parameter's interpretation beyond the 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?

The description identifies the operation ('Search') and the resource ('loaded curated company profiles'), and enumerates supported query dimensions: name, domain, industry, or ticker. It is clear on its face but does not differentiate from overlapping siblings like company_lookup_auto or company_ticker, so it stops short of 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?

No explicit guidance is given on when to choose this tool over the many company_* siblings such as company_lookup_auto, company_domain, or company_ticker. The demo-mode remark is the only contextual hint, and it does not clarify use cases or exclusions. This leaves tool selection largely to inference.

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