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

The description adds meaningful behavioral details beyond the annotations: it 'leaves on the seat's next slot, inside LinkedIn's limits' (scheduling side effect) and explains that an 'already-decided card is refused' (idempotent behavior). It also frames this as 'the human's tap', clarifying that it substitutes a manual action. No contradiction with the annotations 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 first sentence is crisp and front-loaded with the core action and required parameter source. The second sentence carries behavioral context, though the metaphorical phrase 'human's tap, moved from the cockpit to the chat' is slightly tangential. Still, every sentence serves a purpose and the length is appropriate for a tool with side effects.

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 one-parameter tool with no output schema, the description covers the critical aspects: when to call (after explicit yes), what it does (approves and schedules), side effects (within LinkedIn limits), and idempotent failure mode (refuses already-decided). It does not detail return values, but the annotations and simplicity make this a minor gap.

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?

While the schema's approvalId description is minimal ('The card to approve.'), the tool description adds crucial context: the ID comes from gtm_list_approvals and refers to a single drafted action. This helps the agent know exactly what value to pass and where to obtain it, exceeding the schema's bare 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 states a specific verb ('Approve'), a specific resource ('drafted action'), and the exact identifier source ('by its approvalId (from gtm_list_approvals)'). It also scopes the operation to 'ONE' drafted action and notes that already-decided cards are refused, distinguishing it from gtm_reject without naming it. This is clear and actionable.

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?

The description gives an explicit condition: 'ONLY call it after showing them the draft and getting a yes in this conversation.' It also implies when not to call (if already decided). However, it does not explicitly name the alternative gtm_reject for rejection cases, relying on the reader to infer from sibling context.

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