whale-alerts

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

No annotations are supplied, so the description carries the full burden, and it discloses almost nothing behavioral: no read-only confirmation, no result limits or pagination, no ordering, and no indication of what a returned row contains. The embedded parameter notes do cover the min_usd default (100,000) and that start_ns/end_ns bound transaction date for equities, which is genuinely useful context, but that is scoping detail rather than the tool's operational behavior.

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 top-level description is a single front-loaded sentence with zero waste, which is good. But the accompanying schema text is bloated with internal file/line citations and cross-surface rationalization (cli.py:4144, api_server.py:2225, mcp_server.py:1400) that is developer rationale rather than agent-facing guidance, so the overall payload is mis-sized in the wrong direction.

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?

Five parameters, three of them required, no output schema and no annotations — this description should be doing far more work. It never says what the returned records look like, whether results are bounded, or how symbol and asset_class interact, leaving an agent able to call it but unable to predict or validate the response.

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 reported at 20%, so the description must compensate, and the embedded text does add real meaning for min_usd (default 100k, why it beats REST's 0.0, and that 0 admits the whole tape) and for the time window (transaction date vs ingestion instant on equities). It says nothing about the expected format or resolution of 'symbol', which is a required parameter, nor does it clarify what the ambiguous enum-inferred asset_class means for crypto symbols that could span venues.

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 the resource (trades and liquidations) and the defining filter (notional above a USD threshold), which is a specific and coherent purpose. It does not, however, distinguish the tool from siblings like query, search, smart-money or mev-sandwich that also return market events, so an agent cannot route between them from this text alone.

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?

There is no statement of when to use this versus alternatives, no prerequisites, and no exclusions. The only routing hint anywhere in the schema text is an aside that a caller wanting the raw tape should ask for 'trade' rows, which is oblique rather than directive.

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