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

Annotations (destructiveHint=true, readOnlyHint=false) only flag that this mutates state; the description goes much further by explaining that omitted fields are preserved, that supplied depends_on/tags/stack_layer_ids arrays REPLACE the stored list and [] clears it, that unknown stack_layer_ids are silently dropped, and which updates are rejected.

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?

Front-loaded with purpose, then usage, then edge-case semantics in a compact paragraph with no filler sentences. It is dense and the final sentences pack several distinct rules together, but every sentence carries actionable information.

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?

Covers the hard parts: ID discovery, partial-update semantics, array replacement, and rejection rules for a tool with nested objects and no output schema. The remaining gap is return behavior (e.g., how to obtain the new task_id), which is not addressed and matters for chained create calls.

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% and the params oneOf already lists every field, so the baseline is 3. The description adds real meaning on top: merge-vs-replace semantics for the three array parameters, the empty-array clearing behavior, and the silent dropping of unrecognized stack_layer_ids, none of which the schema states.

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?

States a specific verb pair and resource: 'Create or update tasks within an Epic,' and adds scope ('materialise a plan into stored tasks with stack-layer assignments and dependencies'). It differentiates itself from read siblings by directing ID lookups to query_context, though it never names list_tasks as the read alternative.

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?

Explicitly routes the agent: this is the Planner Breakdown write path, and existing epic/task IDs must come from query_context domain=backlog reads (action=list_epics, then action=list with params.type="tasks"). It also enumerates the rejection conditions (no-op update, active/claimed task, invalid status transition), which is exactly the when-and-when-not guidance an agent needs.

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