List notes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is the deterministic ordering (`pinIndex DESC`, `createdAt DESC`, `id DESC`) and the cursor-termination behavior — both useful for an agent assembling results. It does not describe note body/return shape or whether notes from related records are excluded.

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?

Four short lines, front-loaded with purpose, then scope, then sort order, then the calling/pagination instructions. The sort-order line is the only possibly optional sentence and it earns its place by explaining result ordering.

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 read-only paginated list with no output schema, the description supplies scope, ordering, and pagination termination — enough to call it correctly. It omits any hint of what a note record contains and just references a raw endpoint path, which a tool-using agent can't resolve.

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% and the schema already states the exactly-one-of `contactId`/`dealId` rule, so the description largely restates it. The "until it is null" cursor loop is the one genuinely additive detail; otherwise the schema does the heavy lifting, which anchors this at the baseline.

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 ("List notes") and narrows the scope to notes "directly attached to the requested contact or deal," which implicitly separates it from the sibling list_note_feed. An agent can pick between the two note-listing tools without opening a 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 selection rule ("Provide `contactId` or `dealId`") and the pagination recipe ("Paginate with the returned `cursor` until it is null"), plus a pointer to the feed endpoint as the contrasting alternative. It stops short of an explicit "use list_note_feed instead when..." statement, so the exclusion is only implied.

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