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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely new context: the call is free because cost was incurred at search-creation time. It also implies the retry pattern via the schema's 'Call again while pending_ids remain', useful for an agent polling a queue.

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?

Two tight sentences, front-loaded with what is returned and what input it expects. The cost note is appended compactly with no filler.

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 no output schema, the description could say more about the returned shape is described by the blocks enum in the schema ('organic', 'ai_overview*'). Given the rich input schema and read-only annotations, what's present is largely sufficient for correct invocation.

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 description coverage is 100%, so all five parameters are already documented in the schema, including the filter, domain, and wait semantics. The description only re-frames ids as 'pending_ids of a previous call', adding little beyond the schema's own text, so the baseline 3 applies.

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 specific verb+resource ('Returns searches already created') and constrains it to google_search/google_maps results keyed by serp_ IDs. It contrasts implicitly with the sibling creation tools (google_search, google_maps), though it doesn't name the sibling list_searches, which is the closest alternative.

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 a concrete usage trigger ('the pending_ids of a previous call') and a decision-relevant fact (it's free because searches were paid at creation). It stops short of explicit when-not guidance or naming list_searches as the way to discover IDs in the first place.

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