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

Annotations only flag readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false; the description goes well beyond that. It discloses that invitation emails are sent in the shopper's name from Plendio, cannot be recalled once sent, that there are caps of 10 addresses per request and 20 people per list, that invitations are rate-limited, and that sign-in is required. Those are exactly the side effects an agent needs before invoking a non-idempotent, externally visible write.

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?

Four sentences, front-loaded with the action and followed by consequences, limits, and prerequisites in descending importance. Every sentence contributes operational information with no restated boilerplate.

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, the description correctly mentions the return value (the share link, when one exists). For a non-idempotent, externally visible, rate-limited write with four parameters, it covers permissions, irreversibility, and quotas — everything needed to call it safely.

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 coverage is 100%, so role, emails, market, and list_id are already documented in the schema, and the description mostly restates the role default and the 10-address cap. It does add one fact not in the schema: the 20-people-per-list ceiling. The market parameter, which controls link localization in the response, is never mentioned in the description.

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 opens with a specific verb and resource: 'Invites people by email to a list the signed-in shopper owns,' plus the role variants and the returned share link. That is far more precise than the bare name 'share_wishlist'. It stops short of naming sibling tools such as list_shares or revoke_share, so the agent must infer the distinction between sharing, listing shares, and revoking them.

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 states an ownership precondition ('a list the signed-in shopper owns') and a recommended confirmation step before sending, which is real usage guidance. However, it never says when to prefer this tool over alternatives like list_shares (to inspect existing shares) or create_wishlist, and there are no explicit when-not conditions beyond the implicit limit caps.

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