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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the description does not need to restate them. It instead adds genuinely new behavioral context: the billing model is pay-per-returned-result, invalid input (400) and upstream failures (4xx/5xx) are not settled, cost is $0.03 USDC via x402 paid inside MCP, and the flag semantics (RED/AMBER/GREEN) are defined with the specific filing conditions that trigger each.

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 with the user questions it answers, then the input contract, then the return payload — a sensible order with no filler sentences. The long enumeration of returned fields is justified because there is no output schema, though the block is dense enough that it reads as a data dump rather than a summary.

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?

There is no output schema, so the description must describe the return, and it does so thoroughly: profile fields, four fiscal years of income/cash-flow/balance-sheet metrics, latest quarter with YoY growth, 8-K and Form 4 detail, latest 10-K/10-Q, flag taxonomy, and the `summary` field. Billing and failure behavior are also covered, leaving nothing an agent needs to invoke it correctly.

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 each of the five parameters is already documented in the schema, and the description mostly restates that any of ticker/company/CIK/domain works rather than adding syntax or precedence rules beyond what the schema says. It does not mention the optional `via` parameter at all. Baseline 3 is appropriate when the schema carries the detail.

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 concrete example questions ('Give me a quick due-diligence read on NVDA') and then enumerates exactly what one call returns — profile, four years of XBRL financials, latest quarter, 8-K events, insider Form 4 activity, latest filings and color-coded risk flags. It also explicitly distinguishes itself from siblings by naming the five calls it replaces (company_profile, sec_financials, sec_recent_events, sec_insider_trades). An agent can tell this apart from sec_financials or sec_alerts_peek without opening any schema.

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 states exactly what input forms are accepted (ticker, company name, CIK or website domain), names the tools it supersedes, and routes follow-up work via next_calls ('what changed in the risk factors and the latest earnings release'). It also states the negative case — unknown, ambiguous or private companies return tickers free and are not charged.

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