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

The description goes far beyond the sparse annotations (readOnlyHint false, openWorldHint true). It discloses the mechanics: initial snapshot, re-fetch every 3600 seconds, deterministic text extraction, hashed change records, and a returned token. It also covers limitations (no JS/login/proxies/bot bypass), failure behavior (BLOCKED reported), and cost model, giving the agent a full picture of what invoking this tool entails.

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?

Though longer than many descriptions, every sentence earns its place: purpose, mechanics, token usage, quota/cost, limitations, and failure handling are all covered. The most important usage context is front-loaded, and the limitations are grouped at the end. No filler or redundancy.

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 asynchronous nature and the absence of an output schema, the description is complete: it explains the single input (url), what happens immediately (snapshot), what happens over time (polling), what the agent receives (token), how to consume results (check_changes), applicable quotas, and edge cases (BLOCKED, remaining checks). An agent can invoke this tool correctly and understand the follow-up steps without needing additional information.

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 schema already documents url as 'Public http(s) URL to watch,' so baseline is 3. The description adds meaningful constraints by explaining that the URL must be plain-fetchable without JavaScript, login, proxies, or bot-protection bypass, and that pages blocking plain fetches return BLOCKED. This sharpens what 'public' means for choosing a valid parameter value.

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 specific verb and resource: 'Start watching a public web page for changes when you cannot stay running yourself.' It clearly distinguishes this from siblings by explaining that check_changes is the follow-up call to retrieve diffs, and unwatch_url is the likely stop operation. The tool's role as the initiation step in a watch workflow is unmistakable.

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?

It explicitly states the condition for use: 'Use when a task needs to know whether a page changed since you last looked, and you will not be alive to check.' It gives concrete examples (price, status page, job listing) and points to the companion tool check_changes for later retrieval. This provides clear guidance on when to select this tool.

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