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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=true; 'Read only; no spend' merely restates them. Nothing is added about whether the 'confirm'/'requestId' confirmation machinery applies to a read, how results are scoped or paginated, or what happens with an unknown accountId.

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?

Short and front-loaded with the verb+resource, which is good. But the trailing 'Fields: soclo://tools/...' line is opaque indirection that conveys nothing to an agent and displaces more useful guidance.

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, a nested filter object, and 50% parameter coverage, the description leaves the agent guessing about result shape and filtering. It also never explains why a read-only tool accepts 'confirm' and 'requestId'.

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?

Six parameters at 50% schema coverage, including a nested 'parameters' object with undocumented 'types' and 'campaignId'. The description adds no meaning for any of them, and the 'Fields:' line points at a soclo:// URI rather than explaining what those fields filter.

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 and resource: 'List Google Ads recommendations'. An agent can distinguish it from the mutating siblings (soclo_ads_apply_google_recommendations, soclo_ads_dismiss_google_recommendations) by name alone, though the description never names those alternatives explicitly.

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?

'Read only; no spend' implies this is the inspection step before applying or dismissing recommendations, but the when/when-not routing to the apply/dismiss siblings is left entirely to inference from their names. No prerequisites (e.g. which account context is needed) are stated.

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