get_calendar_agenda

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

Goes well beyond the readOnly/openWorld annotations: it discloses the caching path, that results include all-day and already-started events, that recurrences are expanded, that end_date is exclusive, and flags event text as untrusted data (a prompt-injection warning). These are exactly the traits an agent could not infer from structured fields.

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?

Three short sentences, front-loaded with the core action and no filler. The compressed phrasing ('Today/tomorrow uses a fast timed-event cache') is dense but readable; a little more spacing between the mode rules would help.

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?

For a parameterless-required, read-only tool with no output schema, this covers modes, format, inclusivity, recurrence, caching, empty-result handling and safety warnings. The remaining hole is sibling disambiguation against show_calendar_agenda and any hint of the returned shape.

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?

With 0% schema coverage the description carries the whole load and mostly does: it defines the day enum's meaning, the ISO YYYY-MM-DD format, the exclusivity of end_date, and a 366-day span cap. It omits precedence rules when day and dates conflict and whether start_date alone is valid.

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?

Opens with a specific verb and resource — 'Read the existing calendar feed' — which is unambiguous about what the tool returns. It does not, however, distinguish itself from the sibling show_calendar_agenda, so an agent must guess which one renders vs. retrieves the agenda.

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 real usage conditions for the two modes (today/tomorrow via fast cache vs. explicit date range) and warns to 'check available before interpreting an empty result', which is actionable. But it never states when to pick this over show_calendar_agenda, nor what to do if both day and start/end_date are supplied.

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