List note feed

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the burden is lower, and the description still contributes real behavioral detail: the fixed sort order (`pinIndex DESC`, `createdAt DESC`, `id DESC`) and the terminal-cursor pagination contract. Most valuable is the disclosure that the feed is transitive, pulling notes from a related deal or contact, which no annotation or schema field conveys.

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?

Short, front-loaded, and broken into scannable sections covering scope, composition, ordering, and pagination. The 'See also GET /v1/note' cross-reference is the one line that adds little for an agent that cannot issue raw HTTP calls.

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 four optional parameters, no output schema, and full annotation coverage, the definition covers the invocation rules, ordering, and pagination loop adequately. The remaining gap is the shape of a returned note item (fields, whether pinned status is surfaced), which the agent must discover by calling.

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 the per-parameter documentation is already handled; the description nonetheless adds meaning by explaining what passing `contactId` versus `dealId` actually returns (direct notes plus notes from the related entity). The cursor parameter is only restated at a high level, not given extra semantics.

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 note feed') and defines the feed as scoped to a contact or a deal. The scope distinction from a plain note listing is made explicit, though the sibling tool `list_notes` is never named, so the agent must infer the difference between the two.

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 clear invocation context: supply exactly one of `contactId` or `dealId`, and paginate using the returned cursor until it is null. It does not, however, say when to choose this tool over the sibling `list_notes` or `get_note`, leaving that selection to inference.

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