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

Far beyond what the annotations say (readOnlyHint=false, destructiveHint=false, idempotentHint=false). It discloses the non-obvious outcomes: non-account emails return connected:false until the recipient confirms by link, telegram returns connectUrl/connectGroupUrl and stays disconnected until someone taps Start, the link expires in 24h and requires delete+recreate, and the 20-channel-per-account cap.

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?

Purpose is front-loaded in the first clause, followed by kind-specific rules in roughly schema order. It is dense but nearly every clause carries operational information; the telegram and email sentences are long run-ons joined by semicolons, which slightly hurts scannability.

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 3-parameter mutation tool with no output schema, the description covers what an agent needs: required vs kind-dependent params, the disconnected-then-confirmed lifecycle, how to check state afterward, how monitors get attached, and the account limit. Nothing material is left to inference.

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 100%, so the baseline is 3, but the description adds real meaning: the target must be a publicly reachable webhook URL and is ignored for telegram, and label is capped at 100 characters — a constraint the schema does not encode. It does restate the kind→target mapping already present in the schema, which keeps it below 5.

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 first sentence states a specific verb and resource ("Cria um canal") and its purpose: delivering monitor down/recovery alerts to the team. Within the sibling set (listar_canais, remover_canal, testar_canal, vincular_canal) it is unmistakably the creation operation, and the per-kind rules make the scope concrete.

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?

Guidance is strong: which kinds take an email vs a public webhook URL, that telegram omits target entirely, and that the new channel starts with no monitors — binding is done via vincular_canal, and state is verified via listar_canais. It never states when not to use it (e.g., reusing/vouching for testar_canal or remover_canal in the 24h-expiry case beyond the recreate instruction), so it falls just short of full when/when-not coverage.

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