Messages

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

Adds real context beyond the annotations: on legacy accounts the folder choice mutates the view Librus remembers (explaining a non-readOnly listing tool), and archived listings cannot be filtered. It doesn't cover rate limits or what next_cursor/page bounds look like, though the schema and output schema handle the latter.

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 what the tool returns and the alternative before the branch details. Dense but largely justified; the legacy/modern sentence packs two distinct facts and reads as slightly compressed.

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 an output schema present, return-shape details aren't required, and the description still summarises the exposed fields. For a 9-parameter paginated tool with backend branching it covers the decision-relevant facts, though credential/scope prerequisites are unmentioned.

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 100%, so the baseline is 3; the description earns a bump by adding semantics not in the schema — that filters only apply to current mail, that archives are unfilterable, and that filters must be identical across cursor pages. It still doesn't clarify the legacy page_size=50 constraint or cursor shape itself.

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 (list message summaries) and names the exact fields returned, plus explicitly contrasts with get_message_content for message bodies. An agent can distinguish it from siblings like get_message_unread_counts or get_message_correspondents without opening the schema.

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 explicit routing: use get_message_content for text, this tool for summaries. It also spells out the branch condition (legacy vs modern accounts), that archives cannot be filtered, and that follow-up pages must repeat the same filters with the cursor.

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