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

Annotations already provide readOnly/idempotent/destructive hints. The description adds a long-poll timeout behavior, default status, and a security warning that task text is untrusted, all beyond the schema and annotations. No contradiction.

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 front-loaded with purpose and keeps behavioral notes in short separate sentences. 'Read-only' is redundant with annotations, and the provenance clause is slightly dense, but overall it is tight and scannable.

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 an optional-parameter read-only list tool it is mostly self-sufficient: it explains provenance, default status, polling, and trust. It under-documents limit and inbox_id and, with no output schema, does not describe the return shape, so there are still usable but non-trivial gaps.

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?

Only 'wait' is documented in the schema (25% coverage), and the description merely restates that wait is a long-poll with max 25. It adds the pending default for status, but limit and inbox_id receive no semantic help, leaving a substantial gap.

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 ('List') and resource ('actionable tasks') with precise provenance conditions (verified owner/allowlisted sender, DMARC/DKIM alignment). This distinguishes it from message-centric siblings like cooper_get_message and cooper_list_messages.

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 operational context: default status pending, long-poll behavior, and read-only nature, so an agent understands typical calling conditions. It does not explicitly name alternatives or say when not to use it, but the task-vs-message split is implied by sibling names.

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