Dates changed since

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered by structured data and the description need not restate it. The description adds a modest hint that this is a polling/sync endpoint, but does not explain caching behavior, ordering, or what a "change" means — the only cache-related detail ("fresh") lives in the schema, not the description.

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?

It is a single short sentence with no filler, which is good, but it is front-loaded with an ambiguous noun rather than a verb, and the trailing clause "as the panel polls them" is vague jargon that occupies space without resolving the core ambiguity.

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 carries the burden of saying what is returned, and it does not — the shape of a "date with changes" entry is never described. For a delta/polling endpoint where callers must know how to interpret the result and whether to pass the returned value back as a new timestamp, this is a significant gap.

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 100%, so both parameters (timestamp with its Unix-seconds note, and the fresh cache-bypass flag) are already documented in the schema. The description's phrase "since a Unix timestamp" echoes the schema rather than adding format, granularity, or edge-case semantics. Baseline 3 applies.

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 the resource ("dates with calendar changes") and the filtering dimension ("since a Unix timestamp"), but never uses a clear verb and leaves "dates" ambiguous — it is unclear whether this returns calendar days, appointment records, or change markers. It also fails to differentiate from the very similar sibling "appointment_changes_feed", so an agent cannot confidently tell the two apart.

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 indication of when to use this tool versus the many calendar siblings (calendar_month, calendar_agenda, appointment_changes_feed). The phrase "as the panel polls them" hints at a sync use case but is not framed as guidance or as an exclusion criterion.

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