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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, and the description adds the key behavioral fact that this records a proposal and does not alter the schedule. It does not mention downstream review/notifications or the non-idempotent consequence of duplicate submissions, but the central non-effect is well disclosed.

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?

Front-loaded with the most important constraint ('does not change the schedule') and then delivers a dense, non-redundant per-kind requirements list. The run-on 'kind X requires ...' chain is efficient though it would read better as a list; no sentence is filler.

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 9-parameter tool with output schema present (return values need not be explained), the description supplies the conditional field requirements an agent needs to construct a valid call. The remaining gap is workflow context — what happens after a suggestion is recorded and how it gets accepted — which limits it slightly.

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 9 parameters, so the description carries the burden and largely does: it maps each of the six kind enum values to its required companion fields (dueOn, target, paymentId, amountMinor, label, script). It omits guidance on scheduleId, the summary field's purpose, and the meaning of target=deposit vs later beyond the paymentId rule.

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 a specific verb and resource ('Record a suggested change') and immediately clarifies the scope with 'This does not change the schedule,' which cleanly separates it from the applying tool. It stops short of naming accept_schedule_change, the natural alternative a caller would otherwise confuse it with.

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?

The per-kind requirement breakdown effectively tells the caller which inputs select which behavior, but there is no explicit when-to-use guidance relative to accept_schedule_change or commit_schedule. The suggestion-only nature is implied rather than routed ('use accept_schedule_change to apply it').

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