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

With no annotations, the description carries the full burden and does well on the two surprising traits: it states the cost ($0.01/call in USDC on Base eip155:8453) and the exact payment placement in params._meta["x402/payment"], plus the HTTP transport. It doesn't cover error/failure behavior when payment is missing, rate limits, or freshness of the EDGAR data, which keeps it below a 5.

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 payload contents before cost and transport, and every sentence carries information. The middle sales clause ("Saves an agent five separate lookups") is partly puffery, and the full URL plus CAIP-2 chain ID inline makes one very long sentence, but nothing is redundant.

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?

No output schema and no annotations, so the description must define the return surface — and it does by enumerating the four data blocks returned. What's missing is any sense of response shape (flat text brief vs. structured object), size/latency expectations, or behavior when a ticker has no EDGAR match.

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 coverage is 100% and both parameters (q, excerpts) are self-documenting with examples, so the baseline is 3. The description does add one thing the schema omits — that a payment object lives in params._meta — but gives no guidance on the excerpt count tradeoff or on q's resolution ambiguity (ticker vs. name vs. CIK).

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?

Names a concrete verb+resource (joins SEC EDGAR data into a brief) and enumerates exactly what the brief contains: profile, annual financial series with YoY growth and margins, recent filings, risk-factor excerpts. However it never differentiates itself from near-identical siblings like composite__brief, edgar__financials or company_facts__snapshot, and the tool name 'watchlist' actively misleads about the resource, so an agent could easily pick the wrong tool.

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?

"Saves an agent five separate lookups and all the parsing" gives a clear selection rationale: use this when you'd otherwise fan out to multiple lookups. There are no explicit exclusions and no sibling is named as the cheaper alternative for a single-field need.

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