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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new context: a 24-hour retention bound, a 50-record cap, 20 records per page, cursor-expiry error behavior, and an explicit warning that this is bounded runtime metadata rather than permanent chat memory. The trailing sentence 'No paths, parameters, output or credentials' is opaque and does not map cleanly onto any disclosed behavior.

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 core facts (retention, caps, paging, filters, cursor reuse) are front-loaded and dense. The closing fragment 'No paths, parameters, output or credentials' is an ungrammatical leftover that adds ambiguity rather than information, and the page-size wording conflicts with the limit parameter.

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?

With an output schema present, the description is not obliged to explain return values, and it does supply retention limits, pagination behavior, and cursor lifecycle. The main hole is the ambiguity between the stated '20 per page' and the caller-controlled limit parameter, which could lead an agent to mis-set or ignore it.

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% across 5 parameters, so the description carries real weight; it does explain that from_ms/to_ms filter on started_at in UTC milliseconds and that status is a filter. However it never mentions the limit parameter explicitly (its '20 per page' phrasing could be read as a fixed page size despite limit being caller-supplied up to 20), and it gives no defaults or bounds for the time range.

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 names a specific verb and resource: paging metadata records of tool calls scoped to the current OAuth account, with a 24-hour retention window. It is clear what is being listed, but it never names or distinguishes itself from siblings such as list_remote_tool_calls or agent_history, so an agent must infer the boundary.

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?

It gives operational guidance for continued paging (reuse the cursor with identical filters, expired cursors yield a stable error) and describes the filter surface. It does not say when to choose this over the similarly-named alternatives in the sibling list, so selection guidance is only implied.

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