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

Annotations already establish read-only, idempotent, open-world behavior, so the bar is lower, and the description adds real context beyond them: results are capped at 40, ordered biggest-first, include each filter's reading, and are judged on PumpPill's side. No contradiction. It stops short of covering error cases (invalid code, empty rule) or refresh cadence, so not a 5.

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 return value is front-loaded in the first clause, followed by param provenance, result contents, the non-recommendation caveat, the workflow hint, and the cap/ordering. Five dense sentences, all carrying information, though the 'judged by PumpPill on its side' phrase is slightly awkward.

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 single-parameter, read-only tool with no output schema, the description adequately covers what comes back, how many items, in what order, and what each item contains. The main omission is behavior for the optional/empty `rule`, which is the one thing an agent could get wrong.

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 0%, so the description carries the param burden and mostly does: it defines `rule` as the code with a concrete prefix format (pp1....) and tells the agent where the user obtains it (pumppill.org/customize). The gap is the unexplained empty-string default and whether the call is meaningful without a rule.

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 names a specific resource (Robinhood Chain tokens), a specific operation (those passing every filter of a member's rule), and the evaluator (PumpPill, server-side). It explicitly separates itself from recommendation-style siblings by stating a pass is 'a match to the member's own rule, not a recommendation.' An agent can distinguish this from best_calls/premium_calls_recent without opening any schema.

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 implies when the tool applies (checking which tokens currently satisfy your rule) and gives a workflow hint to 'compare with the last check to find NEW passes.' However, it names no alternative sibling and gives no when-not guidance, and it never explains how the tool behaves when the optional `rule` is omitted despite the empty default.

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