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

With no annotations provided, the description carries the full burden for behavioral disclosure. It does well by revealing the near-real-time nature, the default time window, cursor semantics, and supported change reason types. It does not mention response shape or pagination behavior, which would add further transparency, but the core behavioral traits are clearly 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?

Three compact sentences, each earning its place. The description opens with the tool's identity and endpoint, then gives cursor semantics, default behavior, supported reason types, and a usage example with an explicit alternative. There is no fluff or redundant restatement of schema details.

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?

Despite having no output schema and no annotations, the description gives an agent everything needed to select and invoke the tool correctly: endpoint, cursor mechanics, default window, state filtering, reason types, and the suitable use case. The only minor omission is the exact response structure, but the feed semantics are clear enough for a 4-parameter optional 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema: it clarifies that `since` should be the newest already-seen timestamp, gives a concrete state example ('Florida' / FL), and enumerates meaningful reason types. `limit` is not elaborated in the description, but the schema already documents it clearly.

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 uses a specific verb and resource: 'Near-real-time feed of what changed (GET /v1/changes).' It clearly states the tool's scope and differentiates it from search_bills by positioning it as a changes feed rather than a search endpoint. An agent can immediately understand what this tool does and how it differs 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?

The description explicitly says when to use it: 'Use this for monitoring and incremental sync — "what moved in Florida since yesterday" — rather than re-scanning search_bills.' It also gives practical polling guidance with `since=<ISO timestamp>` and explains the default last-hour behavior, leaving no ambiguity about the intended use case.

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