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

Annotations already flag destructive and idempotent, but the description adds substantial non-redundant behavior: UPSERT semantics, one-note-per-node limit, the exact error reasons (ref_path_not_found with matched_prefix/candidates, adl_unavailable), the fact that "$ref" targets are not followed, and the contexts/useCases naming trap. This is far beyond what the annotations convey.

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 the core action and auth requirement, then layers constraints, error semantics, and output shape in a dense, orderly block. It is long, but nearly every sentence carries distinct information; only mild redundancy with the schema descriptions costs it the top score.

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 mutation tool with no output schema, the description supplies the required params, the auth/permission model, the overwrite semantics, the failure modes, and even the response shape ({ ok, mode, defined_at, updated_at }). An agent has everything needed to call it correctly and interpret the result.

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 the parameters are already documented, and the description's parameter notes (200-char normative text, ref_path server validation, lang) largely restate the schema. The ref_path matching/candidates detail is useful but already mirrored in the schema description, so the 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?

States a specific verb+resource: saving a normative humanNote onto an ADL node, and explicitly notes the UPSERT overwrite behavior with a max of one effective note per node. It is clearly distinguishable from the read/delete siblings (get_notes, delete_note) without opening any schema.

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?

Gives the precondition (login required, editor or admin role) and points to iceshore://guide/common for the draft-then-save workflow. It does not explicitly name when to prefer this over siblings like delete_note/get_notes, so it stops short of full when/when-not guidance.

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