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

Beyond the readOnly/idempotent annotations, the description discloses behavior like 'unchanged: true and no rows' and the cost context ('Free tier', 'cheapest poll available here'). However, it references a `next_since` field that does not exist in the input schema, which slightly muddies the behavioral contract.

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 description is four short sentences with zero filler: it leads with the purpose, then the polling behavior, the free tier, and the alternative. It earns every sentence.

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 full parameter schema, safety annotations, and a clear description of the response behavior for the unchanged case, the tool is well-covered. The only notable defect is the `next_since` naming conflict, which prevents it from being fully seamless for an agent.

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 100%, so the schema already documents all three parameters. The description adds a usage pattern (send previous `next_since` and `etag`) that gives context, but it misnames `since` as `next_since`, so the added value is limited and potentially confusing.

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 action: 'Return only the funds whose data changed since a given timestamp' with a clear resource (funds) and a specific time-based scope. It also explicitly differentiates itself from search_funds by saying to use this instead of re-running a schedule, so an agent can distinguish it from siblings.

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 an explicit 'use this instead of' statement and concrete polling guidance: send the previous response's since/etag values, and expects 'unchanged: true' with no rows when nothing changed. This tells the agent exactly when and how to use this tool rather than running a full search.

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