agent_delete_message

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

With no annotations, the description carries the full burden and does so well: it discloses the destructive side effect visible to the other party ('The other party can see that it is gone'), the off-by-default gating via an env var, and the auth context ('Acts as the identity in the local credential store'). It omits confirmation/undo behavior, but the key behavioral risks are surfaced.

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?

Four compact sentences, front-loaded with the action and its scope, then the visibility consequence, then the gating and identity context. Each sentence carries distinct information, with only mild density in the env-var clause.

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 one-parameter delete with no output schema and no annotations, the description covers scope, permission, side effects, gating, and identity context — enough for an agent to decide and call correctly. Only the irreversibility/confirmation story is left implicit.

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% for the single message_id parameter, so the schema already documents it. The description adds permission semantics ('sender or recipient only') but no format or id-sourcing guidance beyond the schema, so baseline 3 applies.

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?

States a specific verb+resource ('Delete a message by id') and immediately scopes it with '(sender or recipient only)', which distinguishes it from agent_send_message, agent_mark_read, and the memory/capability delete siblings. It stops short of naming an alternative explicitly, but the purpose is unambiguous.

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?

Gives concrete conditions for use and non-use: only the sender or recipient may delete, and the operation is refused unless the human owner sets VOIDLY_MCP_RELAY_ALLOW_STATE_CHANGES=1. That is clear when-to-use guidance, though it never points to an alternative tool for adjacent needs.

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