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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world). The description adds real behavioral context beyond that: the payload is a paired old/new value with links, and critically it 'says what changed and never what it means' — warning the agent not to expect interpretation. It does not clarify the default time window or paging behavior, which keeps it below a 5.

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 tight sentences with no filler, and the payload shape is front-loaded ahead of the interpretive caveat. Nothing to cut.

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 no output schema, the description carries the burden of describing return values, which it partly does (paired old/new values with both links). The gap is the days parameter: an agent cannot tell what window 'recently' covers or what happens if days is omitted, which matters for a change-feed tool.

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%, with limit (1–200, default 50, envelope reports true total) and offset well documented in the schema itself. The description's 'recently' vaguely gestures at the undocumented days parameter but never states its default or unit, so it adds little beyond the schema.

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 concretely what the tool returns: figures publishers restated, each paired as an old value and a new value with both links. That is specific enough to distinguish it from list_figures or record_overview, though it never names the closest sibling (figure_history) to sharpen the contrast.

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?

There is no explicit when-to-use statement, no prerequisites, and no mention of alternatives such as figure_history. The agent must infer from 'restated recently' that this is the change-feed view, and must guess how it differs from history lookups.

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