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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint:false, so the safety profile is covered. The description earns credit for adding non-obvious context beyond that: the upstream source (Yahoo Finance via yfinance), that no API key is needed, and the exact shape of the response (earnings_history, earnings_dates, earnings_estimate). It does not explain caching or how the inherited fin-style filters affect behavior.

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?

Front-loaded purpose sentence, scannable when-to-use bullets, then return structure and source in two short lines. Every sentence carries information and there is no repetition of the title or annotations.

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?

The presence of an output schema means return values need not be detailed, and the description still helpfully names the three sections. However, for a tool whose only parameter is a schema with zero description coverage at the top level and contains unrelated fin-specific filters plus an optional ticker, the description leaves key invocation questions (is symbol required? what scope do the extra filters have?) unanswered.

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?

The description says nothing about the single `params` object — no mention of `symbol`, `limit`, or that symbol is optional and defaults to null (what happens then is unstated). Worse, the schema carries fin-domain plumbing parameters (wholesaler_ids, exclude_fillers, mcp_prompt_id, source_resource_id) that are unexplained by the description and unrelated to earnings data, leaving the agent guessing which of these actually matter.

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+resource (fetch earnings history: EPS actual vs estimate, surprise %, upcoming earnings dates, forward estimates) and enumerates the three returned sections. It is distinguishable from neighboring tools in practice, but it never explicitly contrasts itself with GetAnalystRatings or GetFinancials, which an agent could plausibly confuse with 'consensus estimates'.

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?

Three explicit 'Use this tool when' bullets give clear triggering contexts (performance vs expectations, next earnings date, surprise trends). There are no exclusions or named alternatives for the near-miss cases, so it stops short of a 5.

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