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

With no annotations, the description carries the full behavioral load and does so: free accounts see which changes are tracked and which have a result, but no numbers; results are newest first; 'early' means too little traffic to judge rather than failure. That last note is exactly the kind of interpretation trap an agent would otherwise fall into, and the pagination block contract (returned, total_available, truncated, next_offset) is spelled out with a warning not to conclude from a truncated slice.

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 long but front-loaded: capability, then use cases, then tier limitation, then ordering, then a labeled PAGING block. The tier and 'early' caveats are essential and not repeated elsewhere, but the paging instructions partially duplicate the offset parameter's own description, which costs a little economy.

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 and no annotations, and the description fills both gaps: it enumerates what the rows contain, defines the direction values including the ambiguous 'early', states ordering, and documents the pagination envelope every list in the response carries. An agent needs nothing else to call it correctly or interpret the result honestly.

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 the baseline is 3, but the description adds real meaning: it explains the paging strategy (read the rest via next_offset, or raise limit) and frames site scoping as 'the caller's sites'. It also connects the parameters to the response's pagination block, which the schema alone does not do, though a few details are duplicated between prose and schema.

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 states a specific verb and resource: show the changes logged for the caller's sites, drawn from three named sources (Track_Change, the Murkuz editor, marking an Action Item done), plus the outcome of each change. It names the exact result fields (direction, clicks per day before/after, percent change, average position, 7/14/28-day checks), so an agent can tell it apart from Track_Change, which logs changes rather than reporting outcomes.

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 concrete user phrasings that select this tool: 'did that change work?', 'what did my last edits do?', 'which changes lost traffic?'. What it lacks is an explicit exclusion or a named alternative for the adjacent case, such as tracking or editing changes via Track_Change, so the routing is clear but not exhaustive.

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