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

Annotations already declare the read-only/idempotent safety profile, but the description adds substantial behavior beyond them: no live Search Console call, rate limiting only against abuse, the Search Console connection prerequisite, and a three-state result contract with explicit branching instructions. This is exactly the kind of context annotations cannot carry.

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 with purpose, then behavior, then the state-branching contract, and essentially every sentence earns its place. It is dense and slightly long, but there is little waste; the state-branch guidance in particular is load-bearing.

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?

There is no output schema, so the description must carry the return semantics — and it does, spelling out all three states, warning that findings may legitimately be empty, and noting coverage as the proof. For a read-only report tool with no output schema, nothing an agent needs to interpret results is missing.

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 100%, so most parameter text is redundant with the schema. However the description adds genuine meaning: window's earlier period is the same length immediately before (not a calendar split), the defaults are this codebase's own and not a vendor formula, and a page dropping out of the top-200 reports recentClicks: 0. That is real semantic value over the documented parameters.

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 precise verb+resource+scope: 'Finds pages whose clicks declined by a meaningful amount between two adjacent windows,' and immediately clarifies the data source (MisarSEO's archived Search Console history). It explicitly contrasts itself with the sibling get_cannibalisation_report, so an agent can route without opening either schema.

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?

Gives clear selection context: read-only, FREE, spends no Google quota unlike get_cannibalisation_report, and requires Search Console to be connected. It names one alternative and the condition that differentiates it. It does not enumerate when this beats other GSC-based siblings like get_search_console_performance, so it stops short of full when/when-not coverage.

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