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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the description's 'Read-only' restates structured data rather than adding to it. The genuinely additive details are the country-scoping ('for the user's own country') and the explicit list of actions that are refused, which tells the agent this tool answers rather than acts. No output schema exists, yet nothing is said about response shape (e.g., whether carrier-specific codes come back as a single value or a list).

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?

Two sentences: the first front-loads purpose and scope, the second carries the read-only boundary. The topic list is long but each item maps to a real enum value, so it earns its space. Slight redundancy in restating 'Read-only' alongside the annotation.

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 simple two-parameter, read-only, closed-world tool with full schema coverage and no output schema, the definition covers what an agent needs to invoke it correctly, including the full topic taxonomy. The only missing piece is any relationship to the near-duplicate sibling 'osmo_help'.

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% and the seven-value enum plus the carrier example ('Jio', 'T-Mobile') and its conditional use are fully documented in the schema itself. The description's topic enumeration merely mirrors the enum and its carrier phrasing implies the same forwarding/carrier_care pairing the schema already states. Baseline 3 is appropriate — the description adds no new parameter meaning.

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 ('Answers OsmO help questions') and then enumerates the exact topic set (forwarding codes, carrier care numbers, plan contents, privacy, account deletion, languages, contact), which lets an agent match a user request to this tool immediately. The one gap is that it never distinguishes itself from the similarly named sibling 'osmo_help', leaving an agent to guess which of the two handles a generic help request.

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?

The enumerated topic list functions as an explicit when-to-use condition, and the closing clause ('making calls, changing plans and deleting the account are not done here') draws a clear when-not boundary for action requests. It stops short of naming the tools that should handle those excluded actions (place_call, update_settings), so the routing advice is one-sided.

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