outlook_upload_task_attachment

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

Annotations only say this is a non-read-only, non-destructive write. The description goes well beyond that: it discloses the inline base64 POST mechanism, the resolution scope of file_path (inside the configured attachments directory), and the 20 MiB ceiling with the reasoning (30 MB Graph body cap, 4/3 base64 inflation) and the up-front refusal behavior. Auth requirements and return payload are not covered.

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 in the first clause, followed by the size bound. The second paragraph explaining the 30 MB/4-3 rationale is slightly verbose but earns its place by making the ceiling credible rather than arbitrary.

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?

No output schema exists, so return values need not be described, but the description also says nothing about what happens on success or failure beyond size refusal. With two of three parameters undocumented and no annotation detail on write behavior, it is adequate but leaves real gaps for a write tool.

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 carries the full burden. It explains file_path semantics (resolves inside the configured attachments directory) and the size constraint tied to it, which is genuinely useful, but task_id and list_id go entirely undocumented beyond their self-evident names.

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 with scope: 'Attach a local file to a To Do task.' The 'To Do task' qualifier implicitly separates it from mail/draft attachment siblings such as outlook_attach_to_draft and outlook_send_with_attachments, but no sibling is named explicitly.

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 implied by the name and the size ceiling acts as a de facto precondition, but there is no explicit when-to-use guidance and no stated alternative for attaching to mail vs. tasks. An agent must infer the routing from the sibling list.

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