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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the description's job is to add shape information – and it does, disclosing the pagination model and what the payload contains ('neutral titles and latest run status only'). The explicit statement of what is NOT returned (messages, source-derived titles) is valuable scope information an agent cannot get from annotations.

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?

Two sentences, zero filler, mechanism front-loaded and the exclusion clause last. Every clause carries information not already present in the schema or annotations.

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-value documentation is not required, and the description still summarizes the payload shape plus its omissions. For a two-parameter read-only list tool this is essentially complete, with only cursor-acquisition mechanics left implicit.

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 0%, so the burden is on the description, and 'bounded cursor pagination' does communicate the paging contract at a high level. It stops short of explaining how a cursor is obtained (presumably from a prior response) or what the bound on limit is, leaving the agent to read the JSON-schema constraints for min/max and default.

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 assistant conversations') and immediately qualifies the mechanism ('bounded cursor pagination') and the exclusions ('does not expose conversation messages or source-derived titles'). That cleanly separates it from the other list_* siblings (list_ideas, list_posts, list_publications) without needing their schemas.

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?

Usage is implied – enumerate conversations via cursor paging – and the negative statement about messages hints at what this tool is not for. However, no sibling is named as an alternative and there is no explicit 'when to use this instead of X' guidance, so the agent must infer routing from the resource name alone.

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