withdraw_message

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

Annotations already flag destructive and idempotent, but the description adds substantial context beyond them: content and audit history are retained, server activation after reader qualification is required, previews/injected context are not recallable, and idempotency-key replay behavior (including replay while execution is disabled or sender closed). This is a genuinely richer behavioral profile than the annotations alone.

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?

Front-loaded with the operation and its scope, then layered with return values, recipient rules, retention guarantees, and activation/idempotency constraints. Every sentence carries new information with no filler.

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?

No output schema exists, yet the description names the return fields (message_id, revision, per-recipient withdrawn/already_withdrawn/too_late results), states retention behavior, and covers the activation prerequisite and idempotency contract. An agent has everything needed to invoke it correctly.

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%, so the baseline is 3 and the schema already documents all five parameters. The description nonetheless adds meaning beyond it: the recipients parameter's subset-validity and omit-for-all semantics, and the replay/conflict behavior of the idempotency key, are reinforced in context rather than left purely to the 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?

States a specific verb (withdraw) applied to a specific resource (your message) with an explicit scope limit (recipients whose delivery has not been read, acknowledged or withdrawn). This clearly separates it from siblings like acknowledge_message, mark_message_read and send_message without needing to open any 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?

Gives clear applicability conditions: it only affects unread/unacknowledged/unwithdrawn deliveries, recipients may be omitted for all or given as a nonempty valid subset, and previews/injected context cannot be recalled. It doesn't explicitly name an alternative tool, so it falls short of a full 5, but the context for use is unambiguous.

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