xlsx_describe

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds that the tool does not silently flatten merged cells or drop named ranges, which is useful behavioral context. However, it does not elaborate on other aspects like authentication or rate limits.

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 moderately concise with front-loaded key information, but it could be more streamlined. It includes a useful pandas comparison and usage guidance, but the lack of parameter details is a structural gap.

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?

Given the tool has a nested options parameter with three sub-properties and no output schema, the description fails to explain how to use these parameters or what the markdown table output contains in detail. This leaves significant gaps for the agent.

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 input schema has 0% description coverage, and the tool description provides no information about parameters such as file_b64 or options (header_row, max_rows, sheet). The agent must infer usage solely from the schema names, which is insufficient.

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 it performs a pandas-style df.describe() per column, listing statistics like count, nulls, unique, min/max/mean/std for numerics, and dtype with purity score. It distinguishes itself from a naive pandas approach and explicitly mentions returning a markdown table, making the tool's purpose unambiguous.

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 includes explicit 'USE WHEN' and 'DO NOT USE WHEN' sections, guiding the agent to use this for quick summaries of local .xlsx files and to avoid it for uploaded files or in-memory data. It also compares favorably to xlsx_read for speed, but does not name specific sibling alternatives like xlsx_value_counts.

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