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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description goes beyond them by disclosing the model's calibration basis (716-event backtest) and its directional accuracy (53% upside, 45% downside and an implied ~50/50 downside), which is genuinely valuable for setting expectations about a probabilistic forecast.

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?

One long but front-loaded sentence leads with purpose, then evidence, then return shape. The nine-factor list is dense but earns its place by explaining what drives the score. A reader can stop after the first clause if they only need the purpose.

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 single-parameter read-only tool with annotations and an output schema, this is close to complete. The closing enumeration of return fields partially duplicates the output schema, so it is slight redundancy rather than a true gap.

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?

There is a single parameter with 100% schema description coverage, and the schema already documents the ticker format with examples. The description adds nothing about the parameter, so the baseline 3 applies.

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 gives a specific verb+resource ('Get earnings surprise probability for a company') and immediately qualifies it as a beat/miss prediction from a 9-factor model, which separates it in spirit from siblings like get_earnings_preview or get_consensus_estimates. It stops short of explicitly naming a sibling it is not, which is the only thing keeping this from a 5.

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 when-to-use guidance, no prerequisites, and no named alternatives among the ~140 siblings. The agent is told what the tool computes but not when to reach for it over get_earnings_quality, get_earnings_preview, or get_consensus_estimates.

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