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

Annotations already cover read-only, non-destructive, non-open-world behavior. The description adds substantial behavioral detail: tasks and findings expire 30 days after creation, pagination can return an empty page with a continuation cursor, and status summaries are recorded rather than fetched from upstream analyses.

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?

Front-loads the core list operation, then layers usage, expiration, pagination, and exclusion notes. The six sentences are information-dense, though the final sentence about professional service requests is somewhat tangential.

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?

An output schema exists, so return format need not be explained, and annotations cover the safety profile. The description supplies expiration timing, pagination edge cases, and recovery/status-summary use cases, completing the context an agent needs.

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 67%: cursor and invention_id have descriptions, while limit has none. The description restates the optional innovation filtering and adds pagination behavior, but provides no semantics for limit, so it only partially compensates for the schema 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 and resource: lists the current user's unexpired automated tasks in the connected organisation, optionally for an innovation. Scope is clear, but no sibling tool is named to explicitly differentiate from get_task_status, list_innovations, or delete_task; the note that professional service requests are separate is too vague to count as sibling routing.

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 usage context: recovers task IDs after a lost response or conversation, and returns recorded status summaries without polling upstream analyses. It also excludes professional service requests, but does not name an alternative tool or provide an explicit when-not condition beyond that.

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