resolve_messages

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 thoroughly: single transaction, sets resolved_at=now(), does NOT mark read, does NOT delete (still visible under all/history/resolved), idempotent silent-skip behavior, and the registration-timing edge case that can block sender-resolve. It also lists auth binding, return shape, and error codes, covering the safety and mutation profile an agent needs.

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 purpose and when-to-use, then Behavior, Returns, and Errors in a clean progression. It is dense and long, but the scope rules and edge cases justify most of the length; a few sentences (e.g. the impersonation reassurance) could be trimmed without loss.

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 mutation tool with no annotations and no output schema, the description supplies the return structure inline (resolved_ids, resolved_count, requested_count, blocked_by_recipient_registration, note) and enumerates the errors (AUTH_FAILED, VALIDATION, RATE_LIMITED). Nothing an agent needs to invoke it correctly is 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 100%, so the baseline is 3, but the description adds real meaning beyond the schema: agent_name is token-bound with "no impersonation path," and message_ids eligibility (unknown/foreign ids silently skipped) is explained rather than just listed. It stops short of adding syntax-level detail for message_ids, so a 4 rather than a 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?

States a specific verb+resource ("Permanently resolve (ack) specific messages") plus the effect ("so they leave your pending queue for good"). It explicitly distinguishes itself from the sibling get_messages path that drains and resolves in one call, and from the orthogonal read/observation plane. An agent can tell exactly what this does and what it is not.

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 explicit when-to-use: "PARTIAL handling — you've actioned some of your mail but not all," and names the alternative for the common case: prefer get_messages(status='pending', ack=true). It also lays out scope rules (recipient-resolve vs sender-resolve, never resolve mail addressed to a real agent), which is exactly the kind of when/when-not routing a strong definition provides.

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