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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known; the description goes beyond that by specifying the cascade effect (all enrollments are removed) and by bounding the blast radius ('não afeta os contatos em si, só a matrícula'). That is exactly the kind of consequence detail annotations cannot express. It stops short of stating the return value or whether deletion is soft/hard at the storage level.

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?

A single tight paragraph that front-loads the destructive/cascade warning before the mitigation note. The emoji-prefixed category label is decorative overhead, but the rest is dense and waste-free.

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 2-parameter destructive tool with full annotation coverage and no output schema, the description supplies the essential missing piece: what gets destroyed beyond the entity itself and what survives. It does not describe permissions or confirmation flow, but target_user_id's admin restriction already lives in the schema.

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 100%, with both sequence_id and target_user_id documented including the admin-only restriction on target_user_id. The description adds no parameter-level detail (no mention of where the ID comes from or of the impersonation parameter), so it sits at the baseline for a fully documented schema.

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?

Specific verb ('Apaga permanentemente') plus a precisely scoped resource ('uma cadência de prospecção') and an explicit cascade scope ('TODAS as suas matrículas'). An agent can distinguish this from sibling delete_* tools (email templates, KB docs, quick replies) purely from the text, which anchors the resource in the prospecting-cadence domain.

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 says 'use com cuidado, especialmente em cadências de teste que ficaram órfãs', which hints at the typical use case (cleaning up orphaned test sequences) but never states when NOT to use it, what the alternative would be for recovering or retiring a sequence (e.g., update_sequence, list_sequences), or any prerequisite confirmation step.

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