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

Annotations only say readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description goes well beyond: mutation paths require api:account, plan caps answer 403 tier_limit_exceeded, add_x_handle validates existence on X (400 user_not_found_on_x when it does not), and add_telegram_group joins/screens the group asynchronously (~20 s) and may be rejected so the group is not added. These are the operational traits an agent needs before invoking.

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 general framing and auth rules are front-loaded before the action-by-action detail, and every clause carries information — return fields, error codes, async caveats. It is a single dense block, however, and a line-per-action breakdown would have been easier to scan for an eight-action 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?

For an eight-action, seven-parameter mutating tool with no output schema, the description covers what it must: return fields for the list actions (handle/is_news_source/name, id/title/username_or_invite/joined_at), action-specific parameters, auth and cap failure modes, and the slow screening step. Nothing needed to call it correctly appears to be missing.

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 86%, so the baseline is 3, but the description materially enriches several params: it documents identifier formats ('a public @username, t.me link or invite link'), points group_id at list_telegram_groups as its source, notes handle works 'with or without @', and binds each parameter to the actions that consume it. Some restatement of schema constraints (limit 1-20, prefix 1-15) dilutes the gain.

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 opening sentence names the resource precisely — 'YOUR custom news sources: the X handles and Telegram groups Gambit reads for you, and which of Gambit's curated news sources are on' — and each of the eight actions is then given its own specific verb+object. An agent can distinguish this config-management tool from read-only feeds like get_news_feed or get_news_headlines without opening the schema.

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 states the auth split ('Reads need api:read; changes need api:account') and the cap consequence (403 tier_limit_exceeded) with an explicit pointer to get_plan_usage for remediation. Per-action descriptions establish when each action applies. It stops short of explicitly naming alternatives or when-not-to-use cases, so it is strong context but not full routing.

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