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

The description explicitly describes a write/bulk-add operation ('Add up to thousands of accounts at once'), while annotations declare readOnlyHint=true and destructiveHint=false. This directly conflicts with what the agent would infer from the description, and no additional behavioral context (permissions required, failure handling for partial batches) is present.

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 text is one incomplete fragment ending in an open parenthesis and ellipsis. It is not verbose, but it is structurally broken and leaves the reader without a complete instruction, which is worse than a slightly longer complete sentence.

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 mutation-style bulk operation with 0% schema coverage, no output schema, and annotations that contradict the described behavior, the description should explain the csv-vs-members choice, offset semantics (pagination?), and required permissions. None of that is present and the text is truncated.

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 full burden for four parameters. It only partially explains `csv` (columns acct,role,team with role values member|admin) and is cut off before finishing; `org`, `offset`, and `members` — including the key question of whether csv and members are alternatives — are entirely undocumented.

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?

"Add up to thousands of accounts at once" gives a verb (add) and a resource (accounts) plus a scale hint, so the core purpose is inferable. But the sentence is truncated mid-clause, and 'accounts' is never tied explicitly to 'org members' or distinguished from sibling tools like org_members or org_member_remove.

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?

No when-to-use guidance is provided: nothing says when to use bulk CSV ingestion versus the `members` array parameter, nor how this relates to org_members (listing) or org_member_remove. The truncated text suggests more was intended but no routing guidance survives.

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