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

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing this as a safe read tool. The description adds value by disclosing the fee structure ('$0.01/call, x402 (USDC on base)'), explaining the returned data includes 'form, filing date and a direct document URL', and referencing the SEC EDGAR rate limit ('10 requests/second'). This goes beyond annotations by adding cost and output context, though it could mention pagination or result limits if applicable.

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?

The description is two sentences long (one for purpose, one for filtering and output details) plus a cost line. Every phrase is essential: the verb 'Watch', the supported forms, the data source, the cost/payment info are all front-loaded. There is no fluff or repetition of the tool name, making it a model of conciseness.

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 simple filtered-list tool with 100% schema coverage and clear annotations (readOnlyHint, destructiveHint), the description is nearly complete. It covers inputs (tickers, form types, lookback), outputs (form, filing date, document URL), cost, and constraints. It loses one point because there is no output schema, so the description's mention of returned fields is essential but could be slightly more precise (e.g., example of the direct document URL format). Still, it is adequate for an agent to invoke 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%, with each parameter having a detailed description (e.g., 'Stock tickers to watch for new SEC filings', 'Only include these SEC form types', maxItems constraints). The tool-level description reinforces usage by listing key parameters (form type, lookback window) and the returned fields. Since the schema already explains all parameters well, the description adds value by summarizing the overall flow, but does not significantly deepen parameter understanding beyond the schema. Baseline 4 for complete schema coverage with some additional context.

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 starts with a specific verb ('Watch') and clearly identifies the resource (stock tickers for new SEC filings). It lists supported form types (10-K, 10-Q, 8-K, S-1) and distinguishes itself from the many job/real-estate/listing siblings by focusing on SEC EDGAR financial data, which is a unique domain among siblings. The phrase 'Official SEC EDGAR data, free, no API key or login' further clarifies its scope and accessibility.

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?

The description provides clear context for when to use this tool (to watch stock tickers for SEC filings) and lists key constraints ('free, no API key or login', rate limit reference). It implies it's for financial/ticker monitoring, which distinguishes it from job, real estate, or tender alert siblings. However, it does not explicitly state when NOT to use it (e.g., for non-US filings, or for real-time stock prices) or name a specific alternative sibling, so it gets a 4 rather than a 5.

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