Add notes

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

Annotations already declare non-destructive, idempotent writes; the description goes further by explaining that duplicates are skipped and reported, that HTML is escaped and newlines become <br> unless allow_html is set, and what dry_run returns without writing. These details are all consistent with destructiveHint=false and idempotentHint=true. It does not, however, describe whether notes are created atomically or what happens on partial failure.

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?

Front-loads a two-sentence summary of the core guarantee and then switches to a per-parameter reference list, which is scannable and wastes little. A few lines (e.g. the prefix-matching example) are dense but each carries real decision-relevant 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?

With an output schema available the description needn't explain return values, and annotations cover the safety profile, so what remains is parameter behavior and duplicate semantics, both thoroughly addressed. An agent can construct a valid call from this description alone.

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 0%, so the description carries the full burden and does so: it gives the notes object shape with a concrete example, explains case-insensitive and prefix field matching to the note type, the model default resolution chain, what tags apply to, both values of duplicate_scope, and the effect of allow_html and dry_run. Only the deck parameter itself is left implicit, which is self-evident.

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?

Opens with a specific verb+resource: 'Add notes to an existing deck', which clearly separates it from anki_update_notes, anki_move_notes, and anki_find_notes. It never names a sibling to redirect to, but the create-only semantics ('existing notes are never overwritten') make the boundary inferable.

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 is implied rather than stated: the no-overwrite and duplicate-skip behavior tells an agent this is the safe way to create new content, and dry_run is offered for verification. There is no explicit 'use this instead of X when Y' guidance, no prerequisite that the deck must already exist as a callable condition, and no exclusion rules.

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