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

Beyond readOnlyHint/openWorldHint the description discloses cost (free, no paid market values), a 90-day retention limit subject to source permissions, the distinction between source dates/digests and retrieval times, and that no reconstruction is possible before the first baseline. That is meaningful behavioral context a caller could not get from the 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 with the core purpose front-loaded and no filler. Density is high (cryptic phrases like 'no paid market values or reconstruction before the first baseline'), but every sentence does carry distinct 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?

No output schema exists, so the description carries the burden of explaining the return shape; it names digests and source dates but never says a next_cursor and a list of change entries come back. The limit parameter and the baseline-recovery path are also left to the schema's partial hints.

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?

With 67% schema coverage the schema already documents scope and cursor, and the description largely restates the scope versioning (instrument v1, market/access v2 with independent cursors). It adds the genuinely useful idea of per-scope independent cursors, but the limit parameter and its default remain undocumented everywhere.

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 opening sentence states a concrete resource and mechanism: cursor-based Treasury change notices, i.e. a delta feed rather than a full history. It falls short of a 5 because it never contrasts itself with siblings like get_rwa_history or compare_rwa_snapshots, so the agent must infer which read tool this is.

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?

No explicit 'use this when…' guidance and no named alternatives, even though the sibling set contains several overlapping read tools. The only implicit usage cues are the 90-day retention note and the mention that reconstruction is impossible before a baseline, which hint at preconditions but do not route the agent.

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