register_prediction

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

With no annotations supplied, the description carries the full behavioral burden. It does disclose a genuinely useful trait — that the registration time is sealed by the ledger and git, implying immutability and an auditable timestamp — and clarifies that probability is the agent's own stated confidence. It says nothing about permissions, whether a registered prediction can be amended or retracted, or what happens if the check cannot be evaluated.

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 purpose is front-loaded in the first sentence and the worked example earns its space by disambiguating the op/value/baseline interaction that the schema cannot convey. The final sentence about the ledger is terse and relevant; only the probability sentence is slightly redundant with the parameter name.

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 13-parameter write tool with zero schema coverage and no output schema, the description covers the core semantics but leaves five parameters (case, statement, statistic, hypothesis, resolve_by) with no explanation anywhere. It also gives no indication of what the tool returns on success, which matters since there is no output schema to fall back on.

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 0%, so the description must compensate for 13 undocumented parameters. It adds real meaning for op, value, baseline_start/baseline_end, series, start/end and probability through the worked example, but leaves case, statement, statistic, hypothesis and resolve_by entirely unexplained in both schema and description.

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 opens with a specific verb and resource: 'Register a falsifiable, machine-checkable prediction,' which tells an agent exactly what object is being created and its defining property (machine-checkability). It does not name or distinguish itself from the obvious sibling 'check_prediction', so the boundary between registering and checking is left implicit.

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?

Usage context is implied rather than stated: it explains that a baseline window yields a relative comparison while omitting one makes the value absolute, which indirectly signals when to supply baseline_start/baseline_end. There is no explicit when-to-use versus check_prediction, no prerequisite statement, and no guidance on when a prediction should not be registered.

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