intercom_reply

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

Annotations already flag this as a destructive, non-idempotent mutation, and the description does not contradict those hints. The description adds that it targets pending inbound asks and that 'to' is a sender/session selector, but it does not disclose concrete side effects such as whether the ask is resolved or removed after replying. With annotations carrying the safety profile, a middle score is appropriate.

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?

Two concise sentences, front-loaded with the main action and no redundant phrasing. The only minor flaw is the awkward 'Use to plus which=...' construction, which would benefit from quotes around parameter names, but it remains compact and useful.

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?

The tool description covers the main purpose and the multi-ask selection case, but leaves gaps around the optionality of 'to' (what recipient is used when omitted) and the post-reply effect on the pending ask. No output schema is present, so the return value is also unspecified, which is acceptable for a send action but still leaves room for additional context.

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 descriptions already cover 'to' and 'which'; the description adds the dependency between them (use together when one sender has multiple unresolved asks), which is helpful. However, the required 'message' parameter has no description beyond its name and type, and the description does not clarify what happens when 'to' is omitted. With 67% schema description coverage, this is adequate but not outstanding.

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 action ('Reply') and a specific resource ('pending inbound ask'), which clearly separates it from generic intercom_send and other siblings. The second sentence adds selector nuance, making it even easier to distinguish from intercom_pending and intercom_ask.

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 context for when to use: there must be a pending inbound ask to reply to. It also provides a concrete conditional for using 'to' plus 'which' when one sender has multiple unresolved asks. It does not explicitly name alternative tools or when not to use it, but the intended situation is clearly implied.

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