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

Annotations (readOnlyHint=false, openWorldHint=true) only signal 'has side effects, reaches outside', so the description carries real additional weight: it discloses that the tool is a long-lived monitor whose results arrive asynchronously via webhook or polling, and that it is gated behind payment/partner credentials. It does not say what happens if webhook is omitted or whether monitoring can be cancelled, which keeps it out of 5 territory.

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 core action and trigger list, then two short sentences for the billing and access facts. Minimal waste, though 'the window on sale is 24 hours' duplicates the schema's '24 is the window on sale' and the single long first sentence is dense.

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?

With no output schema, the description does the necessary work of explaining what comes back and how (each alert as a JSON POST to the webhook, or retrievable via get_job). Required vs optional is left to the schema. For a four-parameter tool with 100% schema coverage this is close to complete, missing only lifecycle details such as cancellation or failure behavior.

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 all four parameters (chain, hours, token, webhook) are already documented in the schema, including the 32-44 char / 0x-hex address formats and the 1-72 hour bounds. The description only echoes the 24-hour default and does not add format or constraint detail beyond it, so the baseline 3 applies.

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?

States a specific verb and resource ('watches one token') and enumerates the alert triggers it fires on (dev wallet sells, top holder sells, liquidity pulled, authorities changed, new wallet cluster). It also names the sibling it hands off to ('polling get_job'), so an agent can separate it from get_job and analyze_token without opening a 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?

Explains the two delivery modes (webhook push or polling get_job) and states the purchasable window ('the window on sale is 24 hours') plus the access requirement ('Paid: partner key or x402'). It does not contrast the tool against the analyze_token sibling, which is the one adjacent choice an agent might weigh, so it stops short of full when/when-not guidance.

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