One caller's receipts tape

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

Annotations only cover read-only/open-world/non-destructive; the description adds two things they cannot: a concrete price ($0.02 USDC on Base) and a critical edge-case behavior (an unknown handle returns a charged EMPTY tape rather than a 404). That empty-but-billed outcome is exactly the kind of surprise an agent must know before calling, and it is disclosed plainly.

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?

Purpose is front-loaded in the first clause and the cost/edge-case warning lands at the end where it is most actionable. The middle field enumeration is long but each item is a distinct returned field, not filler. Slightly denser than ideal but nothing is wasted.

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 no output schema, the description carries the full return-value burden and does it well: field-by-field contents, the 100-record cap, the grade taxonomy, and the empty-response case. It stops short of saying whether pagination exists or how the caller scopes beyond the handle, but for a one-parameter read tool it is nearly complete.

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?

There is a single parameter and schema description coverage is 100% ('X handle, with or without @'), so the schema already carries full meaning. The description only implies the parameter via 'one X account' and adds no format guidance beyond what the schema states. Baseline 3 is correct when the schema does all the work.

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 specific verb+resource+scope: 'the most recent 100 calls by one X account,' and enumerates the exact fields returned (post id/URL, capture time, attribution basis, pool, three prices, grade, outcome, cross-chain records). That is far more than a restatement of the name. It does not, however, name or contrast itself with the near-identical siblings robinx_caller / robinx_callers, which is the one gap keeping it off 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?

Usage is only implied: 'the receipts behind the free report card' hints at a relationship with the report flow, and the empty-tape note signals what happens on a bad input. There is no explicit 'use this when you need per-call grading evidence, use robinx_caller instead when...' routing, so the agent must infer the boundary against a crowded sibling set.

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