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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral detail beyond those: server-side watchId retention, delta-only responses, specific delta types (liquidity ±%, price ±%, became-honeypot, sell-tax spiked, liquidity pulled), pricing, auth-header requirements, and free-tier limits. No contradiction with annotations.

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 core behavior is front-loaded in the first few words, then the flow is explained efficiently. There is some promotional padding ('The second call is worth more than the first'), but nearly every sentence carries operational value for the agent, including pricing and access details.

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 the tool's somewhat unusual two-call retention model, the description is complete: it covers how to invoke each call, what each parameter does, what kind of deltas to expect, the output schema exists, and the access/pricing model. An agent has enough information to select and call it correctly without needing to open the schema.

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?

The input schema covers both parameters at 100%, which sets a baseline of 3. The description adds workflow meaning: tokens are for creating the initial snapshot while watchId is for re-checking an existing list, and it clarifies that the tokens parameter accepts up to 10 comma-separated addresses. This goes beyond the schema's isolated field descriptions.

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 a concrete, question-shaped purpose: 'What changed on my tokens since last check?' It identifies the specific resource (token watchlists) and the unique two-call snapshot/delta mechanic. This clearly differentiates it from sibling token tools like token_compare or price_alert, even without naming them.

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 explicit usage context: 'Built for agents holding positions that re-check daily' and explains the exact two-step sequence — pass up to 10 tokens to snapshot, then call again with the watchId for deltas. It lacks explicit exclusions or named alternatives, but the intended workflow is unmistakable.

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