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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, and the description goes well beyond them by disclosing the daily snapshot cadence, per-market staleness flags, the 30-minute judgment horizon, the correlated-trials caveat on n, and which quality.status values (withheld/degenerate/non_monotone) invalidate a cell. That is substantial additive context, but it is framed as output-reading advice rather than tool behavior, and nothing is said about the cost, latency, or size of the response.

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 front-loaded with a Purpose line and then cleanly labeled sections (Triggers, When to call, Prerequisites, Next steps, Caveats, Output nature) that are easy to skim. The multilingual trigger examples are a little indulgent, but nearly every sentence carries operational value.

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?

Because an output schema exists, return values need not be explained, and the description still covers prerequisites, sequencing, snapshot staleness, and the interpretation traps (nominal n, quality statuses, which aggregate to cite). Nothing an agent needs in order to call and correctly interpret this tool is missing.

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%, so variant, interval, and market_id are already fully documented in the schema, which sets the baseline at 3. The description adds no parameter-level meaning at all — notably it never mentions the variant parameter or explains when the v2 shadow-confidence track is preferable, leaving the schema to carry that decision.

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 verb and resource: reliability-diagram data mapping realized hit rate to Level-1 signal confidence buckets, plus an ECE summary, with a concrete motivating question ('verify whether a 0.9-confidence signal actually hits ~90%'). The scope ('Level-1 signal confidence') implicitly separates it from the macro-layer get_prediction_accuracy, but the similarly named sibling get_structure_calibration is never mentioned, so an agent must still guess how the two calibration tools differ.

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 gives explicit 'When to call' guidance (before trusting get_signals confidence values as probabilities), states 'Prerequisites: none', and names next-step alternatives (get_prediction_accuracy, get_signals). It even enumerates casual trigger phrasings, including non-English ones, so paraphrase queries route here too.

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