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

Goes well beyond the annotations: it discloses that nothing is destroyed on the platform, that hiding is scoped to the default list view, that unmarking fully restores the row, and that the return value is the set of ids actually updated (implying partial success is possible). This is exactly the sort of behavioral context annotations (readOnly=false, destructive=false) cannot convey.

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?

Front-loads the core action, then the consequence of each flag value, then the local-only caveat, then the return value. Four sentences, no filler, every clause carries information an agent needs.

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, the description covers the important return semantics (updated ids) and reversibility. It stops short of describing the full response shape or error/partial-failure behavior, but it is sufficient for correct invocation.

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 every parameter is already documented, including the idempotency key semantics and the 500-id cap. The description restates the is_spam meaning rather than adding new syntax or edge-case detail, so the baseline 3 applies.

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 ('Bulk-flips'), the exact resource and field (`is_spam` on inbox conversations), and the scope (one or more, bulk). It also distinguishes itself from platform moderation and from the read path (`list_inbox_conversations include_spam=true`), which separates it from siblings like mark_conversations_seen.

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?

Explains the two modes clearly: is_spam=true hides rows from the default inbox, is_spam=false clears the flag. It also sets expectations that this is a local flag only, not a platform hide/delete, which steers an agent away from assuming real moderation. It does not name mark_conversations_seen or other siblings as alternatives, so a small gap remains.

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