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

Annotations already declare readOnly/non-destructive/closed-world, so the safety profile is covered. The description does add real behavioral detail beyond that: items come back in a meaningful order, ids must never be shown, empty sections are omitted, and suggestion cards are phrased as questions. It stops short of covering limits, pagination, or what happens when the day is empty beyond the prescribed sentence.

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 purpose is front-loaded in the first sentence, which is good. However, the bulk of the text is persona and rendering scripting ('speaking for Lemongraph, in its voice', 'no emoji', exact salutations), which is lengthy verbatim copy that crowds out tool-level information rather than being concise guidance about invocation.

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 parameters and no output schema, the description carries the burden of describing return content, and it does so reasonably: task cards with title, time, due day or person, and a named source link, plus a separate suggestions section. Terms like 'hired chore' and 'Up next' remain undefined, but an agent can call the tool correctly and render results from this text.

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?

The tool takes zero parameters, so the baseline is 4. The description adds one useful semantic note — that the returned content carries ids which can be reused when the user refers to a numbered card — which is meaningfully more than the empty schema conveys.

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 first sentence gives a concrete verb and resource: retrieve today's 'Up next' items from Lemongraph, including links and context. It is clear what an agent gets back, but 'Up next' is product jargon that is never defined, and no sibling is named to disambiguate it from complete_task or create_task (which are different verbs, so confusion risk is low).

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?

Usage is only implied — an agent must infer that this is called when the user asks what is on their plate today. The only concrete conditional is a follow-up rule ('When the user says a number, use that card's ids'), which addresses post-call behavior rather than when to choose this tool. No when-not or alternative routing is given.

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