intercom_pending

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

Annotations declare readOnlyHint=false and idempotentHint=true, so the agent already knows this is a non-destructive but state-touching operation. The description adds genuine context by disclosing the blocking-wait behavior and that it avoids ending the turn, but it never states what mark_read actually does — i.e. that it consumes unread state so messages may not appear on a later poll — which is the key side effect an agent needs to know before setting it true.

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 sentences with the purpose front-loaded, so the structure is sound and there is no filler. The second sentence, however, packs three undefined internal terms into one clause, trading clarity for density rather than earning its brevity.

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 only two optional parameters, no nested objects, and no output schema, the surface is small and the description covers the polling and blocking modes adequately. It still leaves the mutation semantics of mark_read and the relationship to sibling inbox tools unstated, which are the remaining gaps for a tool an agent may call in a loop.

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 50%: wait_ms is fully documented in the schema (including the early-return behavior), while mark_read has no schema description at all. The description cites both parameters with suggested values (wait_ms: 60000, mark_read: true) but only as a usage recipe rather than explaining mark_read's semantics, so it partially but not fully compensates for the coverage gap.

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 sentence gives a concrete verb and resource pair: reading unread inbound messages and unresolved asks. This is distinguishable from intercom_send or intercom_ask, though the description never names intercom_list or intercom_status, which are the closest siblings and the ones an agent most needs to disambiguate against.

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?

The second sentence describes one specific scenario (awaiting delegated results) and even supplies concrete parameter values, which is real guidance. However, it gives no general when-to-use versus intercom_list/intercom_status, no exclusions, and the scenario is phrased in unexplained internal jargon ('coi', 'native thread queue wake', 'ending the Codex turn'), so an agent not already steeped in that vocabulary cannot apply it.

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