get_vouchers

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

The description outlines the output shape (flat array of specific fields) and clarifies that it respects the date range (scoping correctly, unlike a previous buggy version). It does not mention side effects or error handling, but the readOnly annotation already covers safety. The transparency about what it does not return (no details) is valuable, so a score slightly above average is warranted.

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 heavily padded with irrelevant history about a previous buggy version and the rebuild process. While the key information (purpose, output, alternatives) is front-loaded, the long repetitive explanation about past issues reduces clarity and does not earn its place. It could be shortened by half without losing any essential guidance.

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 covers the essential context: what the tool returns, the filtering mechanism, and when to use alternatives. It does not explain sorting, error scenarios, or pagination, but these are not required for basic invocation. Given the simple nature of a filtered get operation and the provided schema, the description is sufficiently complete.

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 already provides parameter names and descriptions (from, to with date format). The description adds that the tool is 'filtered by date range,' which clarifies the role of these parameters, but does not go beyond that. Since schema coverage is 100%, the additional semantic contribution is minimal, hence a middle score.

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 retrieves vouchers (Day Book) from TallyPrime filtered by date range. It specifies the exact verb, resource, and scope, and distinguishes itself from related tools like get_ledger_vouchers and query_sql by noting it returns header-level data only. This makes it unambiguous for an agent.

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 explicitly tells agents when to use alternatives: 'use get_ledger_vouchers or query_sql for that' when stock item or ledger line detail is needed. This gives clear decision criteria, leaving no doubt about the appropriate context for this tool versus others.

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