search_collect

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds real context by disclosing the external sources (Google/Bing, consistent with openWorldHint) and that output lands in private local storage rather than being returned inline. It does not explain what non-idempotency means here (duplicate rows on re-run?), whether existing local data is overwritten, or auth/latency expectations.

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?

A single front-loaded sentence with zero filler; the verb and destination lead. The problem is under-specification rather than verbosity, which is penalized in the other dimensions.

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?

An output schema exists, so return values need not be described, but the description omits everything an agent needs to invoke this correctly: date-range semantics, what each table enum means, whether 'resume' enables incremental collection, and what 'private local storage' implies for later reads. For a 7-parameter, non-idempotent, open-world tool this is materially incomplete.

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 0% for 7 parameters, so the description carries the full burden and delivers essentially nothing: start/end date range, tables, sources, daily, resume, and page_url are never mentioned. At best, 'Google/Bing' loosely hints at the sources parameter and 'reports' at tables, which is far below what a 7-param tool with undocumented fields requires.

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 (collect), resource (Google/Bing reports), and destination (private local storage), which is enough to distinguish a data-harvesting operation from reporting siblings like search_traffic or search_render_report. It stops short of naming or contrasting any sibling explicitly, and 'search_collect' alone would not have told an agent this pulls GSC/Bing data.

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?

No guidance on when to use this versus search_traffic or search_status, no prerequisites (connected GSC/Bing accounts, credentials), and no indication of when a collection run is appropriate or should be avoided. The agent must infer the entire usage context from the name.

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