list_messages

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

Annotations declare readOnlyHint: true, and the description adds behavioral detail beyond that: it explicitly states that reading does NOT mark anything as seen, which is a critical side-effect guarantee. It also describes the return format (compact cards, newest first) and ordering. This goes beyond the annotation's basic read-only flag, providing agent-relevant behavioral transparency.

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 two sentences with no redundancy. The main purpose is front-loaded, followed by return format details and the key behavioral note about not marking as seen. Every sentence earns its place, and the structure is clean and efficient.

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 moderate complexity (4 parameters, all documented, no output schema), the description covers the essential return format (compact cards with sender, subject, preview, seen state, attachments) and mentions the alternative get_message. It doesn't cover pagination behavior or error conditions, but the limit parameter is documented in the schema and the tool is a straightforward listing operation. It is nearly complete for its purpose.

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%: every parameter (kind, limit, origin, workspace_id) has a detailed description including enums and defaults. The description adds minimal extra semantic value beyond the schema, only hinting at the 'activity log' option via the phrase 'optionally the activity log'. With full schema coverage, the baseline of 3 is appropriate.

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 clearly identifies the tool as listing messages and optionally the activity log in a workspace, referencing the portal's Activity tab. It distinguishes from get_message (full body) and implies a read-only listing operation. The verb 'list' + resource 'messages/activity' + scope 'workspace' is specific and unambiguous, differentiating it from siblings like send_message or mark_messages_seen.

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 provides clear context: it returns compact cards newest first and explicitly points to get_message for full body as an alternative. It also notes that reading does NOT mark anything as seen, which helps avoid confusion with mark_messages_seen. However, it doesn't explicitly state when not to use this tool (e.g., for sending messages) or exhaustively list alternatives, so it's slightly below a 5.

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