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

Adds substantial context beyond annotations: seat-level authorization, side effects ('includeTasks also closes their open tasks'), a conditional scope rule ('includeReplyOwed... in date mode'), and an external-system propagation note ('The Quo inbox follows when the business's write setting allows') that gives meaning to openWorldHint=true. The idempotency retry instruction aligns with idempotentHint=true rather than contradicting it. What is missing is what 'clear' actually does to a thread (archive vs. permanent delete) and whether it is reversible, which is the key unknown for a bulk mutation and creates mild tension with destructiveHint=false.

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?

It is front-loaded with the action and every clause carries information, but the mode/parameter rules are crammed into a single run-on paragraph of nested parentheses that is hard to scan. Splitting the mode rules and the flag rules into separate sentences would improve retrieval without losing content.

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?

For a bulk mutation with six parameters, low schema coverage, no output schema, and open-world side effects, the description covers parameters and permissions well. The remaining gap is outcome semantics: nothing says whether cleared threads are recoverable, whether the call reports how many threads were cleared, or what happens on partial failure when the downstream write setting forbids propagation.

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 only 17%, so the description must compensate, and it does: it defines both enum values of mode, the default and meaning of olderThanDays, that cutoff is an ISO date used as an alternative to olderThanDays, and the effects of includeTasks and includeReplyOwed including that the latter only applies in date mode. That is meaning well beyond the bare schema types.

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 verb and resource with scope: 'Clears every thread older than a cutoff at once, as the inbox's bulk Clear does'. The word 'bulk' plus 'every thread' makes it distinguishable from single-thread siblings like set_conversation_status or disposition_conversation. It stops short of naming an explicit sibling alternative or exclusion, so a 4 rather than 5.

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 concrete selection criteria between the two modes: 'mode date clears threads quiet for olderThanDays (default 14) or since cutoff (ISO date); mode leads clears threads a lead follow-up owns'. It also states the eligibility prerequisite 'owner or admin seats only'. No explicit when-not-to-use guidance or pointer to the single-conversation alternative, which keeps it at 4.

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