Add Inbox Thread Labels

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

Annotations only declare readOnly/destructive/openWorld hints; the description adds real behavioral facts beyond them: the operation is additive and idempotent ("Adding a label the thread already carries changes nothing") and atomic ("If any label ID is not found, nothing changes"). It also states the post-change return content.

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 labeled sections, each one sentence, front-loaded with Purpose and constrained to what an agent needs (scope, exclusions, return, usage). No filler or restated boilerplate.

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?

With no output schema, the description correctly compensates by specifying the return value (all labels on the thread after the change), and it covers failure and idempotency behavior. The only completeness gap is the absence of any contrast with set-inbox-thread-labels, a sibling that also applies labels and could plausibly be selected for the same request.

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 schema already documents inboxId (including the email-address form), threadId, and labelIds (with the 10-item cap). The description only adds ID-provenance hints (list-inbox-threads, list-inbox-labels), which is useful routing rather than parameter meaning. Baseline 3 is appropriate.

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 line states a specific verb, resource, and scope: tag one thread in a Resend inbox with one or more labels, and it immediately clarifies the additive semantics ("Labels already on the thread stay on it"). It also names the operation it is not (remove-inbox-thread-label). The only missed differentiation is against the very similar set-inbox-thread-labels sibling, but the verb choice and additive qualifier still make the purpose unmistakable.

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?

Explicit when-to-use ("User asks to tag, label, or categorize a thread"), explicit when-not (removing labels, creating labels), and named alternatives (remove-inbox-thread-label, create-inbox-label) with prerequisites (create-inbox-label first). It even tells the agent where IDs come from (list-inbox-threads, list-inbox-labels). Only gap is that it never contrasts with set-inbox-thread-labels, the closest sibling.

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