Delimit Ledger Context

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered by structured data. The description adds value beyond that by stating 'Side effects: read-only' and, more usefully, revealing the concrete backing call 'ai.ledger_manager.get_context'. It does not contradict the annotations; the read-only claim aligns with readOnlyHint=true. The minor deduction is because the read-only statement partially duplicates what the annotation already conveys.

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 front-loaded with a one-sentence summary of the tool's purpose, followed by clearly labeled sections: When to use, When NOT to use, Sibling contrast, and Side effects. Every line earns its place. There is slight redundancy between the 'When NOT to use' and 'Sibling contrast' paragraphs, but it is minor and reinforces rather than bloats.

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 simple read-only tool with one optional parameter, everything needed for correct selection and invocation is present: usage timing, exclusions with named alternatives, safety profile (via annotations), implementation detail, and the parameter is fully documented in the schema. An output schema exists, so return-format explanation is not the description's burden. Nothing material is missing.

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% — the single optional 'venture' parameter is already documented in the schema ('Project name or path. Empty = auto-detect from cwd.'). The tool description adds no parameter-level detail, but per the rubric the baseline of 3 applies when the schema carries the full burden, and here it does. No extra credit needed, no penalty warranted.

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 function: 'Quick summary of what's open in the ledger (top 5 by priority)' — a concrete resource (ledger), scope (open items), and constraint (top 5). It explicitly distinguishes itself from the siblings in the same domain: delimit_ledger_list (full list) and delimit_ledger_query (specific item). An agent can tell this tool apart without opening the 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?

Provides explicit When-to-use ('at session start as part of the orchestrator session ritual') and When-NOT-to-use guidance with named alternatives (delimit_ledger_list for full list, delimit_ledger_query for a specific item). The sibling contrast section further reinforces the routing decision. Nothing is left to inference.

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