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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuine non-annotation context: ordering (oldest first), the forward-return framing (price then, a day later, move either way), the aggregate counts plus a summary sentence, and the free-tier restriction of 24 hours. It still says nothing about failure modes or what happens when a coin has no prior events.

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?

It is a single compact sentence with no filler, and the core retrieval behaviour is front-loaded. However, the dense, colloquial phrasing ('counts both ways', 'the record dots', 'the one record sentence') costs comprehension and forces re-reading, so brevity comes at the expense of clarity rather than serving it.

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?

Wait - recalibrating: with 6 optional parameters, 100% schema coverage, a present output schema, and full annotation coverage, the description's remaining job is small. It supplies the ordering, the free-tier limit, and the aggregate-plus-summary output shape, while the schema documents every parameter and the output schema documents the return payload. The only real gap is the undefined 'window', which is a minor omission rather than a blocking one.

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% with enums documented for kind, side and detail, so the baseline is 3. The description mentions only 'one coin' and 'inside your window', and notably references a 'window' that does not appear as a parameter, without clarifying that it is an account-level setting. It adds no meaning to kind, side, limit, cursor, or detail beyond what the schema already states.

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 conveys that this retrieves past occurrences of an unusual event on a single coin along with subsequent price movement, which is a recognisable verb+resource. But the phrasing ('unusual time', 'the record dots', 'the one record sentence') is idiosyncratic enough that an agent must infer that 'unusual time' maps to the whales/forced/fee kinds in the schema. It also does not name or distinguish itself from plausible siblings such as history, situations, or whale_activity.

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 explicit when-to-use statement and no comparison to alternatives like history, situations, or signals, which could plausibly cover overlapping ground. The only guidance is the access note ('Free: the last 24 hours plus the record dots'), which tells the agent about tiering rather than about tool selection. The agent is left to infer usage from the retrieval shape alone.

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