Delimit Next Task

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

The description asserts 'Side effects: read-only on the ledger,' but the annotations declare readOnlyHint: false, which signals the tool is NOT read-only. An agent receives conflicting cues — the structured hint implies possible mutation while the prose claims a read-only operation. The return-action disclosure (BUILD/CONSENSUS/STOP) is valuable, but the contradiction with the annotation forces a score of 1 per the rubric.

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 one-sentence purpose, then tightly organized When/When NOT/Sibling/Side-effects sections. Every sentence earns its place for an agent choosing among roughly 200 sibling tools; no filler or repetition.

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 the output schema and annotations already exist, the description covers everything an agent needs to decide whether to call it: purpose, usage boundaries, sibling contrast, side-effect scope, and the three possible return actions with their meanings. 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 coverage is 100%, so all three parameters are already documented (venture auto-detect, max_risk levels, session_id resume/new). The description only loosely ties max_risk to the 'safeguard checks' concept and adds no per-parameter meaning beyond the schema, so the baseline 3 applies.

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 — 'Get the next task to work on' — and narrows it to the highest-priority open task in a loop session with safeguard checks. It explicitly contrasts itself with delimit_task_complete (closes + advances) and delimit_ledger_list (general listing), so an agent can disambiguate it from a very large sibling set.

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 the full when/when-not/alternatives structure: when to use ('inside a loop session'), when NOT to use (marking done, listing all tasks), and names the exact sibling tools for those cases. 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.