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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Read only' mostly restates structured data; 'no spend' adds a little reassurance about billing. The description never addresses the tension of a 'confirm' parameter described in the schema as owner approval for 'spending/deletion preview' on a tool claimed to be spend-free, nor does it mention openWorldHint implications or rate/availability behavior.

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, which is good, but the third sentence is a bare resource URI that conveys no actionable information to a caller and takes the place where scope or parameter guidance should be. Efficient, but partly wasted.

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?

A read-only call with a nested object parameter, a confirmation/requestId recovery convention, no output schema and no parameter prose needs more than two sentences. The description omits what the prediction contains, what predictionId refers to, and how this fits the create → get → reserve lifecycle.

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 only 50% across 6 parameters including a nested 'parameters' object, and the description adds nothing about accountId, platform, predictionId or the requestId/confirm recovery flow. 'Fields: soclo://tools/soclo_ads_get_rf_prediction' is a URI pointer, not parameter meaning, so the documented gap is entirely uncompensated.

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 a specific verb and resource (get a reach-frequency prediction), which is unambiguous on its own. It does not, however, distinguish this from the tightly related siblings soclo_ads_create_rf_prediction, soclo_ads_reserve_rf_prediction and soclo_ads_cancel_rf_reservation, which an agent will see side by side.

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' hints that this is a retrieval path, but there is no explicit when-to-use, no prerequisite (a prediction must already exist), and no routing to the create/reserve siblings. With four RF-family tools in the list, the agent is left to infer the workflow from names alone.

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