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

Annotations only convey readOnly=false, openWorld=false, destructive=false. The description adds a genuinely non-obvious behavioral disclosure: automatic type coercion where plain numbers stay numeric for SUM()/charts, while '007', '1.50', and >10-digit identifiers are preserved as text to avoid data loss. This is exactly the kind of trait that prevents silent data corruption and goes well beyond what annotations or the schema communicate.

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 core purpose front-loaded in the first. The second sentence is long but every clause earns its place by explaining the coercion rules with concrete examples; trimming it would sacrifice genuinely decision-relevant detail.

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 tool has an output schema, so return values need no description. The description covers the core creation behavior and the trickiest edge cases (type coercion). The one gap is overwrite behavior for existing files at the target path, which is not disclosed; the confirm gate and destructiveHint=false partially mitigate this, but an explicit statement would make it fully 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?

Schema coverage is 100%, so the baseline is 3. The description earns a 4 by adding real meaning to the 'rows' parameter: it explains how values will be interpreted at write time (numbers vs text, leading zeros, long digit runs), which the schema's terse 'Array of row arrays with data' does not convey. Path, headers, and confirm remain schema-described, which is acceptable.

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?

States a specific verb and resource ('Creates a new Excel spreadsheet (.xlsx file)') plus scope ('with headers and optional data rows'). The word 'new' and 'creates' naturally distinguish it from siblings excel_read and excel_write_cell, so an agent can tell them apart without opening schemas.

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?

Usage context is implied rather than explicit: 'Creates a new' signals this is for initial file creation, not modifying existing files. However, the description never names alternatives like excel_write_cell or states a when-to-use versus when-not-to-use rule, leaving the routing to inference.

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