ads_telegram_accounts_sync

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

With no annotations, the description carries the full burden. It does disclose two important traits beyond the schema: that data is written into local SQLite (a side effect for a "read"-sounding name) and that cabinet switching requires confirm=true. It omits auth requirements, whether persisted rows are upserted or replaced, and any rate-limit or failure behavior, so transparency is partial.

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, front-loaded with the action and destination, then the critical confirmation requirement. No filler, no restatement of the name.

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 9-parameter, zero-coverage, no-annotation, no-output-schema tool needs much more: parameter meanings, what "persist" does to existing rows, and what the caller gets back. The description leaves the account/module/project distinctions and the max_ads limit undocumented, which is insufficient for correct invocation.

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 0% across 9 parameters, so the description must compensate. It only covers all ("one or all"), include_stats/stats_period ("optional time-bucketed metrics"), and confirm ("explicit confirm=true"); account_id, module_id, project_id, max_ads, and the project_rules array are entirely unexplained, leaving half the input surface opaque.

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 chain (read + persist) and resource (Telegram Ads cabinets, campaigns, daily spend, time-bucketed metrics) with the destination (local SQLite). It does not distinguish itself from close siblings like ads_telegram_accounts_report or ads_telegram_ads_sync, so an agent cannot tell from the description alone which of these to choose.

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 one or all" implies how the all flag selects scope, and "Cabinet switching requires explicit confirm=true" gives one concrete precondition. However, there is no statement of when to prefer this over ads_telegram_accounts_report, ads_telegram_ads_sync, or ads_telegram_ads_api_sync, and no exclusions are given.

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