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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description does add real value beyond them: monitors with no changes are omitted, and a monitor that changed and reverted is reported as "no net difference" — output-shape behavior the agent couldn't infer. It says nothing about the default 50-item limit or how many monitors a call can cover.

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?

Four short sentences, front-loaded with scope and output form, then use case, then exclusion rule, then mode and edge case. No filler and no repetition of the title.

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 the essentials for a read-only, nine-parameter query tool with no output schema: what it returns, what it omits, and how to choose the mode. It leaves out pagination and truncation behavior, meaning an agent may not know how to page through large result sets or that diffs are capped.

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 44%, below the point where the schema carries the load, so the description should compensate. It explains mode semantics well beyond the enum labels, but says nothing about the other undocumented parameters: limit, offset, context, watches scope, or max_lines_per_watch truncation.

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 verb and resource ("every change across many monitors between two dates") plus the return form ("unified diffs under a header per monitor"), which distinguishes it from single-diff or history siblings. It stops short of naming an alternative tool like get_diff or get_history explicitly, so the contrast is implied rather than stated.

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 an explicit example query ("what changed on my competitor pages this month?") and explains the mode choice as a when-to-use decision: net_change compares period endpoints, each shows every step. It lacks explicit exclusions such as "use get_diff for a single page" and does not mention paging behavior.

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