bulk_mark_read

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

No annotations are provided, so the description carries the burden. It usefully discloses the underlying Graph $batch mechanism and that the operation toggles rather than only sets read state, but says nothing about per-message failure handling, batch limits, or required permissions.

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?

A single front-loaded sentence with no filler. The only cost is terse jargon ('refs', '$batch') that may need unpacking.

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 2-parameter bulk mutation with no annotations and no output schema, the description covers the core action but leaves out failure semantics and batching constraints an agent would need to call it safely.

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 0%, so the description must compensate. It does add real meaning for message_ids by noting 'refs or raw ids', and 'read/unread' hints at the is_read boolean, but is_read is never named and no format details or default (true) are given in prose.

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 ('Mark many messages ... read/unread in one call') and the parenthetical '(refs or raw ids)' plus 'many ... in one call' implicitly separates it from the singular mark_read sibling. It does not explicitly name the alternative, so it stops short of a 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?

Usage is only implied: 'many ... in one call' signals this is the bulk/efficient path versus mark_read, but the description never says when to prefer it, whether there is a batch size limit, or when to fall back to the single-message tool.

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