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

Discloses side effects beyond annotations: acceptance joins the goal and exposes participation to the collaborator; rejection removes the invite from pending. Also warns that there is no persistent dedup key and that the agent should query current state on timeout/unknown results, which is critical for a non-idempotent mutation.

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?

Three dense sentences, each adding operational value: scope/auth, behavior, and failure handling. Information is front-loaded with the most important context first.

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?

Fully covers auth, input source, side effects, non-idempotency, timeout guidance, and post-action verification. Given only two simple parameters and existing annotations, nothing essential is missing.

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 0%, so the description must compensate. It does: inviteId is tied to invites returned by get_my_work, and accept true/false maps to accepting or declining. It stops short of explicitly naming the exact field-to-effect mapping, but enough meaning is conveyed.

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?

Description explicitly states the tool responds to collaboration invites from get_my_work and contrasts accept vs reject behaviors. It clearly differentiates from invite_collaboration_member which sends invites.

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 explicit context: only for personal targeted invites returned by get_my_work, verification via get_collaboration_goal after acceptance, and pending list via get_my_work. Also warns not to auto-resend after unclear outcomes.

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