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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds ordering ('newest first') and the per-run payload contents, which are genuinely useful behavioral facts not in structured fields. It omits pagination behavior, which the limit/offset parameters imply but never explain.

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 waste, with the core payload description front-loaded and the escalation path to get_agent_conversation placed after it. Nothing is redundant with the title 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?

There is no output schema, so the description earns its place by enumerating the returned fields, which an agent otherwise could not know. For a six-parameter read tool with strong annotations, this is nearly complete; the only real omission is any hint about filtering or paging through large result sets.

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 67%, so the schema documents since, until, status, and agent_id, while limit and offset carry only defaults and bounds. The description adds no filter semantics at all — nothing about combining since/until, status values, or how offset interacts with limit — so it does not compensate for the remaining coverage gap. Baseline 3.

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 gives a specific verb and resource ('what the account's agents did') and enumerates what each row contains: agent, status, tools called, credits used, error. It is clearly a run-history listing rather than a task list, though it does not explicitly distinguish itself from close siblings like list_agent_tasks or list_agent_conversations by name.

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?

One alternative is named with a condition ('Read the run's conversation with get_agent_conversation for the full answer'), which is genuine routing guidance. However, there is no guidance on when to use this versus list_agent_tasks, list_agent_conversations, or list_agent_approvals, and no note on when filters such as status or agent_id are appropriate.

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