tg_capabilities

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

Annotations already mark it read-only, idempotent, and non-destructive; the description adds that ceilings are read from Telegram, not guessed, and that only the chat part costs a request. It explains the grouping of blockers by fix type, which is useful beyond the annotations. No contradictions.

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 long but information-dense, starting with a one-line summary before moving to usage and parameters. Every sentence adds either context, a constraint, or a cost warning, so it earns its length.

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 capability-reporting tool with no output schema, the description covers purpose, when to use it, parameters, account behavior, and cost model. An agent has enough to invoke it correctly and interpret the conceptual result without needing more.

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 coverage is 0%, so the description carries the entire load for the three parameters. It explains chat's accepted formats ('id, @username, exact title or "me"') and what it reports, notes the cost implication, and clarifies that chat rights are not reported with all_accounts. This fully compensates for the missing schema descriptions.

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 opens by defining the tool's scope: reporting what this agent can and cannot do and what would unblock the rest. It gives a specific output shape ('N of M tools available, K blocked') and distinguishes this from trying tools and reading errors, so an agent understands this is the capability-introspection tool, not a sibling like tg_status or tg_limits.

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 explicitly says to start here when unsure whether something is possible at all, positioning it as a cheaper alternative to trying a tool. It also gives conditional guidance: pass chat only when the question is about a chat, and use all_accounts when several accounts are signed in. This is clear contextual routing, though it doesn't name sibling tools explicitly.

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