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

Annotations already declare readOnlyHint=true and idempotentHint=true, indicating safe, read-only operation. The description adds that results are 'verbatim from the public record,' aligning with annotations. No contradictory or additional behavioral context (e.g., rate limits) is provided.

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 cover purpose, parameter guidelines, and return behavior with no redundancy. Every sentence adds value, making it highly efficient.

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?

The description fully explains the tool's search capability, required parameters, behavior with empty q, and return fields. Given the absence of an output schema, it adequately describes the output format. No gaps remain.

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?

All four parameters have descriptions in the schema, and the description adds contextual details like 'case-insensitive substring,' 'exact RBI classification as it appears,' and the constraint to provide at least one filter. This goes beyond the schema alone.

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 verb 'Search' and the resource 'RBI's official register of NBFCs', specifying search by substring and optional filters. It distinguishes itself from sibling tools (evidence, failure radar, etc.) by focusing on a specific register.

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 provides clear guidance on required parameters ('Give at least one of q, classification or layer') and hints at browsing behavior ('an empty q with a filter browses that whole slice'). It does not explicitly compare to sibling tools or state when not to use.

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