Delimit Ledger Add

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

Annotations only provide readOnlyHint: false and destructiveHint: false, which are weak generic signals. The description adds meaningful behavioral disclosure: it "writes a new ledger entry via ai.ledger_manager.add_item" and coerces tags/acceptance_criteria/tools_needed from comma strings to lists via _coerce_list_arg. This reveals internal mechanics and transformation behavior an agent needs to predict outcomes. Minor gap: no mention of error behavior or failure modes (e.g., invalid venture auto-detection).

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 tightly organized into labeled sections: purpose, when-to-use, when-not-to-use, sibling contrast, and side effects. Every sentence earns its place, the core purpose is front-loaded, and there is zero filler. The structure makes it scannable for an agent.

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?

Given 13 parameters, 100% schema coverage, an output schema, and annotations, the description covers the decision-critical aspects thoroughly: purpose, alternatives, exclusions, side effects, and coercion. What's missing is prerequisite context — e.g., whether the target project/ledger must already exist, or failure behavior when venture auto-detection from cwd fails. These are real edge cases for a write tool but not crippling gaps.

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 description coverage is 100%, so the baseline is 3 — the schema already documents all 13 parameters. The description adds value beyond the schema by explaining that tags, acceptance_criteria, and tools_needed accept comma-separated strings that get coerced to lists, which clarifies the anyOf string/array types. That lifts it above baseline.

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 opens with a specific verb and resource: "Add a new item to a project's ledger." It then distinguishes itself from siblings explicitly — "delimit_ledger_update changes; delimit_ledger_done closes; this creates" — and from delimit_gov_new_task and delimit_memory_store. An agent can confidently select this tool without inspecting schemas.

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 provides an explicit "When to use" section (work that should outlive the session: tasks, bugs, features, decisions, strategy items) and a "When NOT to use" section naming exact alternatives (delimit_gov_new_task for governance-classed work, delimit_memory_store for quick conversation memory). This is the strongest possible routing guidance.

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