Telegram health check

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

The description contains rich behavioral details, but it explicitly calls this a 'read-only health check' while also stating that session file permissions are 'auto-repaired to 0600'. That auto-repair is a write/side effect and contradicts the readOnlyHint=true annotation.

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 description is compact and front-loaded: it starts with the read-only health-check purpose, then lists checks, return shape, failure semantics, and secrecy guarantees. Every sentence supplies useful information for calling or interpreting the tool.

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, the description fully carries the return contract: { healthy, checks[], account }. It also explains how missing/unauthorized sessions are surfaced, how updates are treated, and that sensitive values are never returned.

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?

The tool takes zero parameters, so there is no parameter semantics burden. The schema is empty and fully consistent with the description, which appropriately says nothing about inputs.

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+resource (read-only health check) and enumerates exactly what is checked: config, installed version, state dir, session presence, session file permissions, and live authorization. It also states the return shape, so an agent can distinguish this diagnostic tool from message/chat operations and login tools.

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?

It gives clear remediation guidance: a missing or unauthorized session is a failed check and telegram_login_start should be called to fix it. It also clarifies that an available update is informational and never fails the check. It does not explicitly say when to use this versus telegram_status, but the diagnostic purpose is clear.

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