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

Annotations declare readOnlyHint=false and destructiveHint=true, implying the tool may mutate or destroy data. The description, however, frames the operation as a read-style discovery action ('Discover companies', 'Returns unique companies'), which contradicts the destructive/not-read-only annotation. This is an annotation contradiction because the description implies a safe, read-only lookup while annotations indicate the opposite.

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?

Three sentences, each with a distinct job: scope and modes, parameter list, and cost/return behavior. No filler or redundant restatement of the tool name. Information is front-loaded.

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 does state that results are unique companies with evidence and company_domains, and it discloses credit costs including free zero-result cases. Missing, though, is any disclosure of the destructive/not-read-only behavior indicated by annotations, and no detail on how the modes combine or what 'evidence' contains, leaving notable gaps for a tool with nested objects and no output schema.

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 22%, so the description must compensate. It names the three modes and explicitly lists optional filters (industries, country_codes, company_headcount, limit) with the limit default and maximum. However, it omits the 'audience' parameter entirely and does not explain the nested structures of 'hiring' or 'company_headcount', so compensation is good but incomplete.

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 ('Discover') and resource ('companies'), and enumerates three distinct discovery modes: hiring activity, technologies in use, and similarity to a company domain. This makes the tool's purpose immediately distinguishable from sibling tools like find_leads or find_posts.

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 description gives clear context for when to use this tool: to discover companies by hiring, technology, or lookalike domain. It does not name sibling alternatives or explicit exclusion criteria, but the use cases are specific enough to guide selection.

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