Decompose Kanban task

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false — the safety bars are loosed, so the burden falls on the description. The description does well here: it discloses that this invokes an auxiliary LLM, writes 'redacted receipts', creates children, links the root, and flips triage to todo — revealing side effects and writing behavior beyond the annotation defaults. This is meaningful context, though it doesn't cover auth requirements or non-redacted data handling.

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?

A single packed sentence that conveys the full flow: POST wrapper, auxiliary LLM, task graph, children creation, linking, triage flip, and redacted receipts. It's dense but front-loads the core action. No wasted words or filler sentences. Slightly over-packed but efficient.

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 has an output schema (so return values are documented elsewhere) and clear param schema. The description captures the main behavioral chain well. However, given this is a mutation tool with no readOnlyHint and involves an LLM call (implying potential for side effects, latency, nondeterministic output), the description could add more on failure modes, mutation scope (what 'redacted' implies about persisted data), or when decomposition is allowed. Adequate but not comprehensive.

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% — the schema already documents 'id' as 'Kanban task id such as t_xxxxxxxx' and 'board' as 'Board slug for the task lookup. Defaults to the configured default board.' The description adds no parameter-specific semantics beyond what the schema provides. Baseline 3 is correct when schema does the heavy lifting and the description doesn't add param detail.

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: 'runs the kanban decomposer auxiliary LLM to produce a task graph, create children, link the root, and flip triage to todo.' This is a specific verb+resource with clear scope. It distinguishes from siblings like hermes_kanban_task_specify (which likely specifies rather than decomposes) and hermes_kanban_task_update. However, it doesn't explicitly name an alternative sibling for differentiation, keeping it at 4 rather than 5.

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 implies usage (decompose a kanban task into a task graph) but provides no explicit when-to-use guidance, prerequisites, or exclusions. There's no mention of when decomposition is appropriate vs. when to use specify/update/create. With a large sibling set of kanban tools, vague implied usage leaves room for an agent to misuse it. No alternatives are named.

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