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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description goes further by naming exactly which actions are destructive: remove, transfer-ownership, leave. That specificity is genuine added value, though it does not cover auth requirements, reversibility, or side effects like notification emails triggered on add.

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?

Two short sentences with zero filler; the action inventory leads and the destructive warning plus sibling pointer are front-loaded. Every clause earns its place.

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 17-parameter multi-action tool, the description covers the action set, the destructive subset, and the read/write boundary with its sibling, while the schema carries the parameter detail and there is no output schema to explain. The remaining gap is per-action parameter pairing, which is only partially implied by schema hints like '(share)' and '(workspace)'.

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 100% across all 17 parameters, with enums and format constraints (e.g., the UTC date format and the 406 rejection note) already documented in the schema. The description adds no parameter syntax or pairing information beyond what the schema provides, so the baseline 3 applies.

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?

Names a specific verb+resource ('Fastio workspace and share members (write)') and enumerates all eight operations, so the agent knows exactly what surface it covers. It also explicitly distinguishes itself from the sibling read tool by ending with 'Reads are on `member`.'

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?

Provides clear routing context: this tool is the write path, and reads belong to `member`. However, with eight distinct actions in one tool, it gives no per-action selection guidance (e.g., when to use 'join' vs 'join-invitation', or 'remove' vs 'leave'), so the agent must fall back on the enum descriptions.

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