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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description goes well beyond that with a hard result cap (newest 50), a stated absence of any continuation token, and the important caveat that an empty result does not prove a connection is missing. Those are operational traits an agent cannot infer from annotations or schema.

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?

Purpose is front-loaded in the first clause and every subsequent sentence carries distinct information (cap, no pagination, empty-result caveat, exclusions). The final sentence is a dense three-item negation that reads as a run-on, which keeps it short of ideal.

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 only two parameters, full schema coverage, an output schema for return values, and rich annotations, the description supplies everything an agent needs: what is listed, the cap, the absence of pagination, the alternative tool for missing files, and the caveat about interpreting empty results.

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%, with both query and agent_id documented as full-text search term and agent ID source respectively. The description only echoes that 'query narrows matches' and adds no syntax, matching scope or null-handling detail beyond the schema, so the baseline of 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?

Uses a specific verb and resource ('Lists Google Picker files selected for Replai') and immediately names the downstream consumer, source_import_drive. It is clearly distinguishable from sources_list, source_upload and provider_connect_handoff, which sit in the same area of the sibling list.

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?

Routes the agent explicitly: source_import_drive imports what this returns, and provider_connect_handoff for google_drive is the alternative when the file is 'absent' from the listing. It also states the inverse condition — that this tool does not upload client-local files, connect a provider or import bytes — which is exactly the exclusion guidance needed to avoid sibling misuse.

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