Delimit Playbook

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

Even though annotations already declare readOnlyHint=false and destructiveHint=true, the description adds precise side effects: save/delete mutate the specific path ~/.delimit/playbooks/, run calls the configured model (a non-obvious external effect with cost implications), and list is explicitly read-only. This contextualizes the annotation flags rather than merely restating them.

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 the core purpose front-loaded, then compact labeled sections for routing and side effects. Every sentence earns its place; the minor overlap between 'When NOT to use' and 'Sibling contrast' is acceptable since one handles routing and the other conceptual differentiation.

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 7-parameter, 4-action tool, the description covers purpose, routing, substitution mechanics, and per-action side effects, and the output schema handles return values. The only gap is that action-to-required-parameter mapping isn't spelled out in prose, but the schema documents this fully at 100% coverage, so the gap is minor.

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%, so the per-parameter baseline is 3. The description elevates this by explaining cross-parameter semantics the schema can't: how {{variable}} placeholders flow from save (template creation) to run (substitution), and how each action maps to side effects. Per-parameter detail is fully in the schema, so the description appropriately focuses on the interaction between parameters.

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 opening line 'Manage reusable prompt templates — save / run / list / delete' names a specific resource (prompt templates) and enumerates its four operations. The sibling contrast explicitly differentiates it from delimit_memory_store ('records info') and delimit_project_config, making it cleanly distinguishable from related tools without opening any schema.

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?

Contains explicit 'When to use' and 'When NOT to use' sections that name exact alternative tools (delimit_project_config for config, delimit_memory_store for memories) and the conditions that route to each. The sibling contrast adds a further conceptual distinction, leaving nothing to inference.

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