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

Annotations only provide readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden. It adds rich context: creation can include a parent+children batch, a scope check runs on every creation, cross-agency assignments are audit-logged, and client is authoritative for tenanting. No contradictions with annotations.

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 description is long but dense and front-loaded: it opens with the core purpose and required client, then dedicates a clear paragraph to decomposition/subtask rules. Each sentence earns its place by providing actionable guidance for a complex 22-parameter tool; the structure helps an agent parse requirements in priority order.

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 complex create tool with no output schema and minimal annotations, the description is sufficiently complete. It covers required fields, prerequisites, sibling alternatives, decomposition handling, cross-agency behavior, and the one-task-per-deliverable rule. The only omission is explicit return-value details, but the description's needs_decomposition guidance effectively tells the agent what to inspect in the response.

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?

Despite high schema coverage, the description adds meaning beyond the schema: it clarifies that client is required for non-subtasks, assignee must be set to self or a teammate, goal and definition_of_done should always be provided, and subtasks should be used for multi-deliverable asks. It also explains the operational consequence of allow_cross_agency and the decomposition response flag.

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 action and object ('turn any client ask into a task') and frames it as step 2 of a working agreement, which clearly distinguishes it from sibling create/update/delete tools. It even names the workflow position and the core rule 'ONE TASK PER DELIVERABLE', leaving no doubt about what this tool does.

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 explicit when-to-use rules ('before you start work'), required preconditions (call list_client_team first, ask for client if unknown), and names alternatives (call request_decomposition for decomposition). It also states behavioral prohibitions: do not begin work on a decomposition-flagged task and do not over-split.

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