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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, open-world action. The description adds a genuinely behavioral constraint not in the annotations: the agent must obtain user consent before deciding. It does not, however, note whether a decision can be reversed or re-issued.

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, front-loaded with the action and followed by the consent rule. No filler; every clause carries meaning.

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 simple 3-parameter mutation with no output schema, the description covers the action and the consent policy, but leaves the required 'conversation' parameter unexplained. Slightly thin, though adequate for such a small surface.

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 only 33% – just the optional token is documented, while the required 'conversation' parameter has no schema description and no explanation in the tool description. The phrase 'on your invite' only weakly hints at what conversation refers to, so the description does not compensate for the coverage gap.

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 pair (approve/deny) and the exact resource (a pending join request on your invite). This clearly separates it from siblings like join_invite (requesting to join) and create_invite (issuing an invite), so an agent can route correctly.

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?

Gives a clear precondition and a human-in-the-loop rule: 'Ask your user first unless they told you how to decide.' It defines when the tool applies (a pending request exists on your invite), but names no alternative tool or fallback, so it stops short of full when/when-not guidance.

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