outlook_list_task_attachments

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

readOnlyHint already establishes the safety profile, so the description focuses on what it uniquely can add: the pagination contract (has_more=True → pass next_cursor back). That is genuinely useful behavioral detail beyond the annotation. It stops short of stating ordering, page-size behavior, or what an empty result means.

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?

Three short lines, each doing distinct work: what it returns, which sibling to call next, and how to paginate. The pagination rule is front-loaded where an agent will hit it immediately after the first call.

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, naming the returned fields and the has_more/next_cursor contract is sufficient to interpret results. However, for a four-parameter tool with zero schema coverage, the undocumented `list_id` and `count` leave a real gap in how to invoke it correctly.

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 the parameter burden, and it only partly does: it explains the cursor/next_cursor round-trip and implies the required task_id. Neither `count` (default 25) nor `list_id` — the latter being a non-obvious scoping parameter — is mentioned anywhere.

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 states a specific verb and resource ('List attachments on a To Do task') and even enumerates the returned fields (id, name, size, content_type). The 'To Do task' qualifier distinguishes it from the mail-attachment sibling `outlook_list_attachments`, so an agent can select it 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?

It gives clear downstream context — use `outlook_download_task_attachment` with an id from this list to fetch content — which is the main reason to call this tool. It describes pagination handling but offers no explicit when-not-to-use guidance or prerequisites (e.g., task must have an attachment present).

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