get_follow_up_candidates

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

Annotations mark the tool as readOnlyHint=true, so the description does not need to reiterate safety. It adds value by explaining the selection criteria (age and pending-on state) and the syncBefore parameter refreshes the index. No contradictions with annotations.

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 two concise sentences that front-load the purpose and usage guidance. Every sentence is necessary and informative, with no wasted words.

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?

Given the tool has 4 optional parameters, no output schema, and annotations indicating a read-only operation, the description covers core functionality and usage context well. It lacks details on output format, but for a filter-and-list tool this is acceptable. The description is complete enough for effective use.

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 parameters are well-documented in the schema. The description adds extra context for 'syncBefore' ('Refresh the local mailbox index from IMAP') and 'pendingOn' enum values, enhancing understanding beyond the schema. Baseline 3 plus additional value yields a 4.

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 states it returns threads overdue for follow-up based on age and pending-on state. It uses specific verbs and distinguishes itself from the sibling 'get_actionable_threads', making the purpose unambiguous.

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?

Explicitly states when to use: 'looking for outbound messages you sent that haven't received a reply, or to surface stale inbound threads.' Also provides a clear alternative: 'Prefer get_actionable_threads for threads where someone is currently waiting on you.' This gives excellent guidance on tool selection.

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