budget_notifications

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

readOnlyHint=true already covers the safety profile, yet the description adds genuinely new context: the result set is filtered to unacknowledged items, it may legitimately be empty, delivery should be restricted to the ledger owner via an authorized channel, and event IDs enable deduplication. These are delivery-side constraints an agent could not infer from the schema or annotations.

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?

Four short sentences, front-loaded with the core purpose and with no redundant restatement of the tool name. The telegraphic, instruction-style phrasing is slightly clipped but every sentence carries information.

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, no output schema and a read-only annotation, the description supplies what is otherwise missing: the filtering semantics of the result set, the possibility of an empty result, and the delivery/dedup contract. It does not describe result shape (count, fields), but the absence of an output schema makes that a minor gap for a simple list 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The mention of 'event ID' refers to fields in the returned notifications, not inputs, and does not create confusion about the empty 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 a specific verb (List) and a narrowly scoped resource (unacknowledged budget-exhausted notifications), which an agent can distinguish from budget_ack_notification's write behaviour. It stops short of naming a sibling explicitly, so it earns a 4 rather than a 5.

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 description implies when the results matter ('Empty list means remain silent', 'Use event ID to deduplicate delivery') but never states when to call this versus budget_status or budget_summary, nor any precondition for the call. Useful handling guidance, no real routing guidance.

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