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

The only annotation is openWorldHint: true, indicating results may not be exhaustive. The description adds 'possible matching records' which aligns with that, but it does not go beyond the annotation. No additional behavioral traits are disclosed (e.g., pagination, ordering, or limitations). Since the annotation is minimal, the description could provide more context but does not, earning a low score.

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 concise: a single clear sentence followed by pricing information. The sentence is front-loaded with the core purpose, and the pricing is appended without clutter. It is well-structured and reasonably sized, though the pricing block could arguably be seen as extra but is acceptable for cost transparency.

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 tool's simplicity (one parameter) and the presence of an output schema (as indicated by context signals), the description does not need to explain return values. It effectively communicates the process (search, get candidates, caller selects) and the optional filter. It is complete for the tool's complexity, though it could mention that results may be partial, but openWorldHint already covers that.

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 covers 100% of the single parameter 'text' with a clear description and examples ('Tesla United States', etc.). The tool description itself does not add further parameter nuances, so the baseline of 3 applies. The schema already provides sufficient semantics, and the description adds no extra value here.

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 clearly states the tool's function: 'Search company candidates by company name, optionally filtered by country or region, and return possible matching records with mapped company IDs for caller-side selection.' This is a specific verb ('Search') with a resource ('company candidates') and distinguishes from siblings like search_region_candidates by focusing on companies. It also mentions the optional filter and the return of IDs, providing a clear scope.

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 implies usage by mentioning 'caller-side selection' (i.e., use this to find candidate companies before further calls), but it does not explicitly state when to use this tool instead of alternatives or provide exclusion criteria. No directional guidance is given, so it is left to inference. This is adequate but not explicit.

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