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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, and the description adds real behavioral context beyond them: the write is non-overwriting and is a no-op on already-annotated datasets. That reconciles the write hint with the non-destructive promise. It does not mention required permissions or what the caller sees when the note is skipped.

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 short sentences, zero filler, with the mutating behavior front-loaded and the overwrite constraint immediately after. Nothing could be removed without losing information.

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 two-parameter tool with full schema coverage and annotation-provided safety profile, the description covers the essential semantics including the no-overwrite rule. The only omission is what the tool returns or signals when it declines to write, which is minor absent an output schema.

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 both parameters ('dataset' and 'description', with lengths and an example) are already fully documented in the schema. The description reinforces that the payload is a short one-liner but adds no naming conventions, dataset identifier format, or length guidance beyond the structured fields.

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 gives a specific verb ('Save a one-line description') and a specific resource ('what a dataset holds'), which is far more precise than the title's restatement. It implicitly distinguishes itself from the sibling note_field by scoping to datasets, though it never names that sibling explicitly.

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 second sentence defines the operative condition clearly: it applies only when a description is missing, and an existing description is preserved. That is effective when-to-use guidance. It stops short of naming an alternative for changing an existing description, which is a gap given the many edit_* siblings.

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