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

Annotations already establish readOnly, non-destructive, idempotent behavior, so the description's additional job is to add behavioral context. It does this well by revealing that date provenance varies (live, published rule, estimate, user) and that the tool intentionally omits non-derivable events. This gives the agent useful expectations about certainty and scope beyond the annotations.

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 description is front-loaded with the tool's scope, then explains provenance and exclusions in the second sentence. Every sentence earns its place: the event list establishes coverage, the provenance sentence shapes expectations, and the exclusion sentence prevents misuse. It is verbose but information-dense rather than padded.

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 compensates by stating that each row indicates its date source and explaining the certainty differences between derived and fixed dates. It also covers intentional gaps like FOMC/CPI. A minor gap is that it does not describe the full return shape or other row fields, but the tool is simple and the provided context is sufficient for correct invocation.

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 100%, and all four parameters already have descriptions in the schema. The description does not add new meaning to days, limit, impact, or symbol, so the baseline of 3 applies. It does not compensate for missing schema information because none is missing.

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 identifies a specific resource—upcoming scheduled events—and enumerates the exact event types it covers (funding settlements, Bitcoin halving, difficulty retargets, options expiry, CME settlement, non-farm payrolls). It also distinguishes the tool from all siblings by stating 'nothing else here looks forward.' This is far beyond a tautological restatement of the name.

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 explicitly says 'Use it before saying anything about what happens next; nothing else here looks forward,' giving a clear when-to-use condition. It also explains deliberate exclusions (FOMC and CPI) because their dates are announced rather than derivable, which indirectly tells the agent not to expect them here. It stops short of naming a specific alternative tool for those announced-event cases, so it is not a perfect 5.

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