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

Annotations only cover safety (readOnlyHint, destructiveHint, openWorldHint); the description adds substantial behavior beyond them: a documented default filter with the exact statistical derivation, the contents of each returned item (caller record, deployer score, FDV), the 24-hour repeat_of de-duplication rule, and an explicit caveat that a measured record describes past calls only. It also discloses cost ($0.02 USDC on Base, waived with a plan key), which is exactly the kind of detail annotations cannot carry.

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 lead clause front-loads what the stream contains, followed by item shape, repeat handling, and pricing in a sensible order. It is dense but mostly earns its words; the trailing '(paid $0.02, or included in a RobinX plan key — see instructions)' partly duplicates the preceding cost sentence and could be merged.

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 takes on responsibility for return shape and does so: it lists the per-item fields, explains repeat_of, and warns that records are backward-looking. Filter defaults, pagination via cursor, and payment terms are all covered, leaving nothing an agent needs in order to invoke it correctly.

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 100%, including the definition of min_rank_score as the 95% Wilson lower bound and the grade-B default of 0.3, so the schema already carries the parameter meaning. The description restates the same default threshold but adds nothing new about min_early_rate or the since cursor beyond what the schema says; baseline 3 applies.

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 resource and qualifier: a pollable stream of fresh Robinhood Chain calls restricted to X accounts with a MEASURED early-call record, further pinned down by the caller-rules-2 criterion (rank_score >= 0.3, Wilson lower bound, >= 4 graded calls, clusters excluded). That is far more precise than a bare 'get signals'. It never names a sibling tool (e.g. robinx_feed, robinx_caller_calls, robinx_omega_signals), so an agent must infer the boundary itself.

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?

'Pollable stream' plus the 'since' cursor implies the intended pattern: call once, then re-poll with the captured_at cursor for new items. However, there is no explicit when-to-use versus when-not-to-use, and no alternative named for agents wanting ungraded calls, single-caller history, or a different signal source, leaving the selection decision implicit.

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