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

With only readOnlyHint=false and idempotentHint=true in annotations, the description carries the load and does so richly: pagination defaults (200/1000), signed watermark cursors, retention limits (30 days or 50000 events), the 410 response on expired cursors, per-page cost (0.01 USDC on Base or Solana), and the explicit 'Never signs payments' constraint. These are exactly the operational facts an agent needs beyond the annotation surface.

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 purpose is front-loaded in the first sentence and each subsequent clause delivers a distinct fact (pagination, retention, cost, idempotency, recovery, payment). It is dense and somewhat telegraphic, but no sentence is filler.

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 payment-gated paginated read tool with no output schema, the description covers pagination, retention, error behavior, cost, and idempotency well. What is left thin is the exact shape of the returned grade/score events, which an agent would still have to discover at runtime.

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 0%, so the description must compensate. It does explain limit (default 200, max 1000), cursor (signed watermark), and idempotency_key usage, but payment_signature's role is only obliquely implied by the cost and 'Never signs payments' lines rather than stated. Three of four parameters are meaningfully covered, leaving a real gap.

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 opens with a specific verb and resource: 'Read ordered new, grade_changed and rescanned events with previous grades and scores.' That is far more precise than a restated name and lets an agent know exactly what domain of data is returned. It stops short of naming any sibling or explaining why it differs from the listing/scan/referral tools, so it does not fully earn 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?

It gives procedural guidance ('use a fresh idempotency key per page', 'retain the original body and proof for exact recovery') but never states when to reach for this tool versus an alternative, nor any preconditions for calling it. With no close sibling in the set, usage is only implied by the resource name.

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