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

The annotations declare destructiveHint:false, implying no destructive operations. But the description explicitly lists 'delete: remove a monitor,' which is a destructive operation on the user's stored monitors. This is a direct contradiction. The description adds other behavioral context (AES-256-GCM encryption, account-tier maximums) but the contradiction is severe enough to make transparency score 1.

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 description is well-structured: a short intro paragraph followed by an action list, with prerequisites at the end. It is longer than typical descriptions, but that length is justified given five actions and nine parameters. There is minor redundancy (e.g., the schema already states action-scoped parameters), but overall it is scannable and front-loaded.

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?

The description covers purpose, actions, storage location, and prerequisites, and the presence of an output schema relieves it from explaining return values. However, the unresolved contradiction with destructiveHint leaves the side effects of 'delete' ambiguous, and there is no mention of error conditions, rate limits, or other operational constraints. These gaps matter for a tool that can modify persistent state.

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 has 100% description coverage, so the baseline is 3. The description does add some meaning by grouping parameters to actions (e.g., 'set only', 'update only') and noting that 'dns' and 'whois' are 'backward compatibility' fields, but these details are already present in the schema's parameter descriptions. No additional semantic meaning is provided beyond what a structured schema would offer.

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 clearly identifies the tool's purpose: 'Manage cross-platform domain monitoring tasks that track changes in WHOIS, DNS, and host-supplied page content.' It also lists the actions (get, set, update, delete, history), which gives a specific verb+resource scope. However, it does not explicitly distinguish itself from the sibling 'domain_changes' tool, which could be confused with the history action, so it stops short of a 5.

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?

Implied usage is present: the description says the tool 'tracks changes' and explains when to use 'get' vs 'history' ('get compares against the previous check only; history answers when a domain changed'). It also states a prerequisite ('Requires a registered account with memory enabled'). Yet it never explicitly says when to choose 'monitor' over sibling tools like 'whois', 'dns', or 'domain_changes', leaving external selection guidance implicit.

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