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

Annotations already mark readOnlyHint and idempotentHint, and the description adds useful behavioral detail by explaining that output separates observed, stale, historical, and absent evidence. It also sets expectations as research rather than a rating. No contradiction with 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?

Three brief, information-dense sentences. The first sentence states the core purpose, the second explains the output taxonomy, and the third sets boundaries. No redundant filler.

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 read-only coverage lookup with two optional parameters and no required inputs, the description sufficiently conveys what the tool does, its scope, its evidence categories, and its limitations. It does not describe the exact result shape, but the evidence taxonomy is clearly implied.

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 documents as_of and provides enum values for sector. The description indirectly explains sector values by naming commercial, small finance, and urban cooperative banks, but it does not explicitly map enum labels to those categories or explain how as_of affects coverage. With 50% schema coverage, the description only partially compensates.

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 ('covered Indian commercial, small finance and urban cooperative banks'), and clearly distinguishes the tool from broader evidence or rating tools by adding 'Separates observed, stale, historical and absent evidence' and 'this is not a census or rating.'

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: free read-only research, coverage-focused, and explicitly says what it is not ('not a census or rating'). However, it does not name sibling alternatives or state when to choose this over tools like evidence_india or universe_search, so it stops short of fully explicit routing.

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