tally_search_purchases

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses: no built-in thresholds ('THRESHOLDS ARE YOURS'), no totals returned ('NO TOTALS'), the meaning of empty results ('returns nothing... That is a real answer, not a failure'), the echo of 'voucherTypesIncluded' for verification, the read-only nature, and even a security warning about text fields being data rather than instructions. This goes far beyond basic mutation warnings.

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 long but well-structured with clear section headers (WHEN TO USE, MATCHING, THRESHOLDS, NO TOTALS, etc.) and a front-loaded purpose statement. Each section addresses a distinct behavioral aspect, so it feels intentional rather than verbose. The only minor detraction is its length, but given the tool's complexity (11 parameters, no annotations, no output schema), it remains appropriately sized.

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 tool with 11 parameters, zero annotations, and no output schema, the description is exceptionally complete. It covers return format ('full vouchers with every ledger entry'), the optional includeAllFields for nested details, default period behavior, the company-loading error expectation, and the significance of an empty result. Even pagination, thresholds, and read-only behavior are explicitly covered.

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?

Although the schema already has 100% description coverage, the tool description significantly extends parameter meaning. It explains matching semantics: 'case-insensitive substring,' 'AND' logic, the specific fields covered by 'query' (voucher number, narration, entry ledger names), that 'fieldMatch' searches nested structures, and that min/maxAmount compare against 'the largest absolute entry amount.' It also clarifies pageSize behavior with the note about TallyPrime not paginating server-side.

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 opens with a specific verb and resource: 'Find purchases in a period matching a party, an amount range, or any field value.' It further clarifies the scope by defining the Purchase family as 'every voucher type deriving from the built-in Purchase type, including company-specific ones,' which distinguishes it from sibling tools like tally_search_sales or tally_search_vouchers.

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 'WHEN TO USE' section explicitly states the intended scenario: 'to narrow purchases down to the transactions of interest — a particular customer or supplier, entries above a threshold, or a reference number.' It also provides practical guidance like 'narrowing the period is the only way to make the query cheaper.' However, it does not explicitly name alternative tools or say when not to use this tool, so it falls short of a 5.

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