find_old_messages

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

With no annotations at all, the description still discloses the return shape (message_ids, count, first 50 summaries), a hard cap ('limit: up to 5000'), and the chaining expectation for bulk tools with confirm_count. It does not state that the operation is non-destructive/read-only or mention permission requirements, which is a gap given annotations are absent.

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?

The definition is short and front-loads the selection rule, then the return shape, then the alternative. The phrasing is telegraphic ('for a bulk tool with confirm_count=count') and slightly compressed, but no sentence is filler.

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 4-parameter read tool with no output schema and no annotations, the description supplies the return payload, the limit ceiling, and the follow-up tool relationship. Remaining gaps are defaults and the exact read_state vocabulary, which the bare schema leaves unresolved.

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 0%, so the description must carry parameter meaning, and it does cover all four: days (age threshold), folder (scope), read_state ('only read or unread'), and limit (max 5000). It does not give the allowed read_state values or the defaults (365/1000/inbox/any), so an agent still guesses at exact strings.

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 plus scope: 'Mail older than `days` in a folder, optionally only read or unread mail.' That distinguishes it from a plain search or list tool, but it never names close siblings like find_old_unread or find_bulk_mail, so the agent must infer overlap.

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?

It explicitly routes one alternative case: 'When the plan is to archive these, archive_matching makes the same selection without passing ids.' It also hints at the bulk-tool confirmation flow via 'confirm_count=count'. What is missing is guidance on when to prefer search_message_ids or find_old_unread instead.

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