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

Annotations already mark this as read-only, idempotent, and non-destructive, so the bar is lower, but the description adds substantial behavioral context: login is required, status semantics are clarified, completion is tracked on claims rather than needs, and the displaying boolean is computed server-side by server clock. It also explains that manual unpublishing does not change status, a non-obvious behavior that could easily be misused.

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?

The description is dense but every sentence carries information: scope, ordering, pagination, sibling routing, status-model warning, and the displaying distinction. The bold headers and structured warnings make it scannable. No filler or restatement of the name or title.

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?

Given the tool's complexity—non-obvious status semantics, a manual unpublish quirk, and overlap with several sibling tools—the description covers all needed operational context. It explains pagination via nextCursor, the displaying filter, and where to get needId. The absence of an output schema is mitigated by explicit mention of the key returned fields (needId, displaying, nextCursor).

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 baseline is 3, but the description adds meaningful semantics beyond the schema: it explains that IN_PROGRESS/COMPLETED/EXPIRED are legacy, that status=OPEN remains after unpublishing, and that displaying must be used instead of status to determine whether an item is still in the feed. This goes beyond what the parameter descriptions alone convey, though the type/limit/cursor params are already well-documented in the schema.

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 states a specific verb and resource: list the current user's published needs, with ordering and pagination. It actively distinguishes itself from siblings by noting that the information feed never shows one's own needs and that this is the route for taking stock of one's own items. It also clarifies the status model, which prevents confusion with other need-related tools.

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 description gives explicit when-to-use guidance: before editing, unpublishing, cancelling, or pulling recommendations, use this tool to obtain needId. It also names the alternative for checking claim completion (get_conversation_needs) and explicitly warns not to filter by status=COMPLETED, giving clear exclusion criteria. This is exemplary usage guidance.

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