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

Annotations flag an open-world, non-idempotent, state-mutating call, and the description goes further with the concrete details an agent needs: baseline persistence across calls, the 2% change threshold, and the $0.005 per-call cost. Since no output schema exists, listing returned fields (baseline, changed, change_pct, added, removed, last_change_ts) is a real addition.

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 question ('Has this page changed...?') followed by tightly packed operational facts — baseline mechanic, threshold, price, sample, return fields. No filler sentences; each clause conveys distinct information.

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 single-parameter tool with no output schema, the description covers the usage model, cost, threshold, and return shape. The one remaining ambiguity is the scope of 'your last call' — how baselines are keyed/identified across sessions is not stated.

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?

One parameter at 100% schema coverage, where the schema already documents 'an http(s):// URL on the public internet'. The description's only extra signal is a free-sample URL example, so it adds marginal meaning over structured data — 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+resource ('has this page changed') and the returned artifact ('text diff'), which cleanly separates it from availability-oriented siblings like site_status. An agent immediately knows this is stateful change detection, not a point-in-time fetch.

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 call-sequence model is explicit: the first call stores a baseline, later calls return a diff against it. That tells the agent when and how to invoke it correctly, though it never contrasts itself with siblings (e.g., domain_profile or site_status) or states when not to use it.

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