steward_spend_today

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

With no annotations, the description carries the full burden and delivers: it discloses in-memory, per-process lifetime, reset-on-restart behavior, that it is a safety rail rather than accounting, and that it incurs no rail call. These are exactly the traits an agent needs to interpret the value correctly.

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?

Two sentences, zero filler, and the identity of the tool is front-loaded before the ephemerality caveats. Every clause adds decision-relevant 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?

For a no-arg, no-output-schema read, the description covers what the value means, its lifetime, and its relationship to the authoritative sibling. The only gap is not stating the literal return shape, which is minor given the meter framing.

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?

Zero parameters, so there is nothing to document; the baseline of 4 applies. The description correctly spends none of its length on parameter details.

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 states a precise resource and scope: 'USDC spent through this process today', and explicitly contrasts itself with the sibling steward_receipts. The verb is implicit rather than stated ('get/read'), but no agent could mistake what this tool returns.

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 clear operative conditions: 'Free, no rail call', and it routes the agent to steward_receipts as the source of truth for settled spend. It does not spell out an explicit when-to-use trigger, but the cost/scope caveats imply the correct context for calling it.

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