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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, yet the description adds genuinely new operational facts: a rate limit of 30 reads per 10 minutes per location and per person, a short cache with an explicit refresh override, a null-with-note degradation path when Google cannot be reached, and the consent rationale behind read-only behavior. This is exactly the context an agent needs before calling.

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?

Three sentences, front-loaded with the payload and followed by operational constraints, with no filler. The middle sentence is dense (cache, rate limit, and read-only rationale packed into one line), which costs a bit of scannability but not clarity.

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?

Given an output schema exists, the description need not re-explain returns, yet it still signals the top-level shape (average rating, total count) and the null/note failure mode. Rate limits, caching, consent restrictions and the identifier chain back to list_workspaces/list_channels are all covered.

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: refresh is framed against 'Shager's short cache' rather than just 'read from Google now', and channel_id is constrained to a list_channels GOOGLE_BUSINESS account. Only workspace_id gains nothing beyond the 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 names the exact resource (reviews of one Google Business Profile location), pins down the identifier source (a list_channels account with network GOOGLE_BUSINESS), and enumerates the returned fields (stars, text, author, dates, owner reply, average rating, total count). This is far more specific than a bare 'list reviews' and cannot be confused with siblings like list_comments or list_channels.

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 states when to use refresh=true (skip the short cache for live Google reads) and redirects the reply workflow away from any agent to Shager's Comments page, which tells the agent what not to attempt here. It does not name a competing sibling for review retrieval, but no such sibling exists, so the guidance is effectively complete.

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