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

Annotations already convey readOnlyHint=false and destructiveHint=false, establishing this as a non-destructive write. The description adds valuable context beyond those flags: it writes a new file next to the source by default, guarantees 'the source is never modified', and discloses the return payload (new file path with row and column counts). This is consistent with the annotations and enriches them with concrete behavior an agent needs.

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?

Three sentences with no waste: purpose first, then side-effect behavior, then return value. Each sentence carries distinct information (what it does, where output goes, what comes back), and the canonical 'Call this tool to...' opener front-loads the decision-relevant purpose.

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?

With no output schema, the description correctly compensates by explaining the return value (new file path plus row and column counts). Combined with 100% schema parameter coverage and consistent annotations, an agent has what it needs to invoke correctly. The only minor gap is the unstated relationship to the sheet_load/sheet_unload workflow — it does not say whether the source file must be loaded in the workspace first.

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 description coverage is 100%, so all four parameters (path, to, sheet, out_path) are already well-documented in the schema. The description adds no parameter-level semantics beyond what the schema states — the 'source is never modified' claim and out_path default behavior are both already present in the schema's parameter descriptions. Baseline 3 applies.

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 opening sentence states a specific verb and resource — 'convert a sheet between excel (xlsx), csv and json' — which clearly differentiates this tool from siblings like sheet_read, sheet_write, sheet_load, and sheet_add_column. An agent can immediately tell this is a format-conversion tool, not a read/write/query operation.

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?

'Call this tool to convert a sheet between excel (xlsx), csv and json' provides an explicit trigger condition for when to invoke it. However, it does not name alternatives or state when NOT to use it (e.g., no mention that in-place editing should use sheet_write). The context is clear but lacks explicit exclusions.

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