intercom_pending

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

The description contradicts the annotations: it says 'Read', but annotations declare readOnlyHint=false and destructiveHint=true, suggesting side effects or mutation. The mark_read parameter's impact is not disclosed, creating a serious behavioral inconsistency.

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?

The description is a single front-loaded sentence with no wasted words. It is concise and structurally efficient, though it omits important behavioral and parameter details that are scored elsewhere.

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 and mixed annotations, the description leaves the return value, side effects, and mark_read behavior unexplained. The annotation contradiction further undermines the agent's ability to use the tool confidently.

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 0%, and the description does not mention mark_read, its default value, or the consequences of setting it to true. The agent cannot understand the only parameter from either the schema or the description.

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 description clearly identifies a specific operation: reading unread inbound messages and unresolved asks scoped to the current Codex session. This distinguishes it from siblings like intercom_send or intercom_reply, which are clearly different actions.

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 description implies a polling/checking use case but gives no explicit guidance on when to use this tool over alternatives like intercom_list or intercom_status. No exclusions or sibling comparisons are provided.

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