gstr1_summary_tool

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

No annotations are supplied, so the description carries the full disclosure burden. It implicitly characterizes the tool as a read-only transformation by describing its output buckets, and it clarifies the tolerated input form ('JSON array (or file path)'), which is real behavioral context. However, it says nothing about what happens to malformed invoices, unmatched rate/HSN entries, whether the summary is lossless or aggregating, or what the returned structure looks like — gaps that matter for a tool with zero annotation coverage.

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?

Two sentences with the purpose front-loaded and the input clarification appended; the bucket list is long but each item carries selection-relevant meaning. No filler or restatement of the tool name.

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 single-parameter summarization tool with no output schema and no annotations, the definition should ideally convey the shape of the result and how partial/invalid invoice data is treated. It covers input handling adequately but leaves the output contract and failure behavior entirely to inference, so it is adequate rather than 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?

With schema description coverage at 0% and the schema declaring only a bare string named 'invoices', the description does meaningful work by stating that `invoices` is a JSON array or a file path — resolving the string-vs-array ambiguity an agent would otherwise face. It does not describe the expected per-invoice fields or the file-path format constraints, which keeps it from a 5.

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 ('Summarise an outward-supply register into GSTR-1 table buckets') and even enumerates the target buckets (B2B, B2C large, B2C others, exports, SEZ, credit/debit notes, HSN memo), so an agent knows this is a classification/aggregation step, not a validation or liability computation. It stops short of naming a sibling such as calc_gst_liability or validate_einvoice to sharpen the boundary, which keeps it at 4 rather than 5.

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?

There is no when-to-use guidance and no exclusions: nothing says whether this should run before filing, after validation, or how it relates to calc_gst_liability or validate_einvoice. The only usage-adjacent information is the input-format note, which is parameter semantics rather than tool selection guidance.

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