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

Annotations already flag a destructive, non-idempotent, open-world mutation, and the description adds real value on top: it is free, it explicitly bounds blast radius ("without starting ads or raising budgets"), and it tells the caller to keep a stable UUID clientRequestId, which is the retry-safety story the idempotentHint=false annotation leaves unanswered. It stops short of explaining what the confirm parameter enforces.

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?

The mutation and its scope are front-loaded and most sentences carry distinct information. A few fragments are thin ("Changes in one call") and the trailing "Fields: soclo://tools/..." doc pointer is unusual, but overall there is little waste.

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?

For a 5-parameter mutation with no output schema, the description covers cost, scope limits, concurrency control, and retry identity, which is what an agent needs to call it safely. Missing pieces are the role of confirm and any hint about what a successful or conflicting response looks like.

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?

With 0% schema description coverage the description has to carry parameter meaning, and it does for four of five: platform (one grant per call), enabled (grants or removes permission), expectedChangedAt (optional stale-change detector, auto-reads current revision otherwise), and clientRequestId (stable UUID to retain). The confirm boolean is never mentioned, which is a meaningful gap on a destructive tool.

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?

"Change one platform auto-pause grant" gives a specific verb and resource and scopes it to a single platform per call, which is clearly not the read counterpart. It does not, however, distinguish itself from adjacent siblings like soclo_ads_watch_set or soclo_ads_watch_ask_first_set, leaving that inference to the agent.

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?

Usage is implied rather than stated: the note about expectedChangedAt explains optimistic concurrency and "reconcile uncertain changes by reading current permissions" points at the read tool for that sub-case. There is no explicit "use this instead of X when Y" guidance against the other watch-set tools, so an agent still has to infer the routing.

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