flag_message

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description adds genuine value by showing that flagging is reversible via -1 and that setting overwrites an existing color, but it says nothing about permissions, failure modes, or what happens with an out-of-range color.

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-loaded with the action, then a compact Args block; the color legend is dense but every entry is informative. No filler sentences, though the docstring-style formatting is slightly less scannable than prose.

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 four-parameter mutation with no output schema, the description covers the non-obvious enum, the clearing value and the identifier provenance, while annotations handle the safety profile. A note on return/error behavior would close the last gap, but nothing essential is missing.

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 carries the whole burden — and it does: color is fully enumerated (0 red through 6 gray, -1 clears) and the three identifier parameters are tied to search_messages output. Only the id/account/mailbox formats are left implicit, which keeps this just short of complete.

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 gives a specific verb and resource ('Set or clear the flag color on a message'), so the effect is unambiguous. It does not position itself against neighbors like mark_read or mark_unread, but no sibling offers an overlapping flagging capability, so confusion risk is low.

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 'As returned by search_messages' note usefully tells the agent where account, mailbox and id come from, which implies the read-first workflow. It stops short of stating when to flag versus when to use mark_read/mark_unread, and there are no exclusions or preconditions.

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