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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description only needs to add context. It does: default to latest snapshot, default to filter-selected content, pagination for multi-monitor calls, and the retention constraint that unfiltered/html data only survives the newest two snapshots. It does not say what happens when a watch string matches several monitors or when no snapshot exists.

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?

It is a single dense sentence with stacked parentheticals, so the useful facts (selection modes, paging, filter default, retention) are present but require re-reading. The purpose statement is front-loaded, yet the fried-cheese example is longer than the rule it illustrates.

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 nine parameters, no output schema, and no required fields, the description covers input selection and filtering well. It leaves the return shape unaddressed: for a multi-monitor or paged call it never indicates whether text comes back per monitor, in what order, or how truncation via max_chars surfaces.

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 coverage is 89%, so the baseline is 3, but the prose adds genuine meaning: it explains the mutual roles of watch vs watches vs tag (one monitor vs several vs a group) and how unfiltered inverts the default filter behavior. That relational context is not fully spelled out in the schema property 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 names a concrete resource (a monitor's page text) and the snapshot-time qualifier, plus the three selection shapes (watch, watches, tag) and paging. It is clearly distinct from get_screenshot or get_diff in substance, but never names a sibling to route the agent explicitly.

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 gives a real when-to-use cue for the unfiltered mode ('for questions its filters don't cover') with a concrete example, which is genuinely helpful. However, it offers no guidance on choosing this tool over get_diff, get_history, or list_snapshots, so the cross-tool decision is left to inference.

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