get_waiting_summary

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

No annotations are provided, so the description carries the full burden. It discloses what the tool aggregates (pending delegations), what is returned (counts per person, oldest item age), and the grouping logic. However, it's a read operation with no safety concerns needing disclosure, and it has an output schema that covers return structure. The 'oldest item age' detail adds useful behavioral context beyond the output schema.

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?

Well-structured with a one-line summary, an illustrative example, a clarification of grouping logic, and a returns section. Each element earns its place. Slightly verbose in the 'Returns' section which repeats info arguably covered by the output schema, but the example and grouping details are valuable context not in the schema.

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?

The tool is simple (zero params, no nested objects) and has an output schema, so the description's job is light. It clearly explains the aggregation semantics, grouping by assignee, and key output fields. For a read-only summary tool, this is reasonably complete. The only minor gap is not explicitly naming sibling alternatives for when a user wants raw lists instead of aggregates.

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?

There are zero parameters, so there is nothing for the description to explain beyond confirming no configuration is needed. With 0 params and 100% schema coverage, the baseline is 4. The description appropriately doesn't waste space on parameter details and instead focuses on what the output means.

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?

Uses a specific verb+resource ('Get a summary of what you're waiting on from each person') and provides concrete examples of the output ('Waiting on: 3 items from Sarah, 2 from Mike'). The phrase 'Groups pending delegations by assignee' distinguishes this from related sibling tools like get_delegations or get_my_commitments by clarifying it's an aggregated, person-grouped view.

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 makes clear this aggregates waiting-on items across people, which distinguishes it from get_delegations (raw list) and get_delegations_to_person (person-filtered). However, it doesn't explicitly state when NOT to use it or name alternative tools for raw/individual delegation views. The intended use case is implied (wanting a high-level overview) rather than explicitly contrasted with siblings.

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