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

With no annotations provided, the description carries the full disclosure burden and does it well: it reveals the payment requirement ('Costs $0.005 USDC per call via x402 (Base)'), the auth model ('no API key, no account'), the failure mode ('Calling without payment returns 402 with the payment requirements'), and the polling duration ('Includes 7 days of polling'). The only notable omission is what a successful watch returns or how results are delivered beyond the webhook hint in the schema.

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?

Four sentences, each carrying distinct, non-redundant information: purpose, duration, cost plus error behavior, and free alternatives. The purpose is front-loaded in sentence one, and concrete numbers ($0.005, 7 days, 24h, 402) make every clause actionable. No filler or restatement of the title.

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?

Given there is no output schema and no annotations, the description must stand alone for invocation decisions — and it covers operational essentials thoroughly (payment, auth, error path, duration, trial alternatives). The real gaps are the cik/ticker selection semantics (which identifier to pass under what condition) and the undocumented success-response behavior for a paid, stateful API. These are meaningful but do not prevent an agent from attempting a correct call, especially with the 402 fallback documented.

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 exactly 50%: webhook and idempotency_key are well documented in the schema, but cik and ticker have no descriptions. The tool description adds only the 'company' context and does not clarify the critical relationship between cik and ticker — whether they are alternatives, both required, or which takes precedence (schema lists zero required parameters). At the 50% coverage boundary, the description neither compensates for the gap nor contradicts it, so the baseline of 3 is appropriate.

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 and resource: 'Monitor a company between agent runs for new Form 4 insider buys, sells, grants, and tax withholding.' This precisely narrows the scope to SEC Form 4 insider-trade monitoring, distinguishing it from siblings like watch_sec_filings (general SEC filings) and check_insider_trades (one-shot check rather than a watch). The title 'Watch a company for insider trades' reinforces the purpose without being a mere tautology.

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 gives clear context: monitoring happens 'between agent runs,' lasts '7 days of polling,' and costs $0.005 USDC via x402 with alternatives offered — 'Free alternative: GET https://longwatch.dev/demo... or POST https://longwatch.dev/try for a 24h watch.' This tells an agent the cost/benefit tradeoff and trial paths. However, it never explicitly excludes sibling tools (e.g., 'use check_insider_trades for one-time queries'), leaving the watch-vs-check distinction implied by naming only.

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