Steer the project (next wave when the queue runs dry)

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

Annotations show readOnlyHint=false, which is consistent with the description's mention of claiming review candidates in steering.json. The description discloses important behaviors: it modifies state by claiming tickets, can report to user, and has a dryRun mode for previewing. No contradictions with annotations.

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 purpose and usage. It contains detailed procedural steps. While every sentence adds value, it is somewhat verbose with numbered steps and parentheticals. Could be slightly more concise without losing key details.

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 no output schema, the description fully explains what the tool returns: 'ordered, executable passes' and the sequence of actions. It covers the full lifecycle, including failure condition and dryRun. For a complex steering tool, this is complete.

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 50% (dryRun has a description, project does not). The description adds meaning: 'dryRun: true to preview without claiming' clarifies its preview behavior. Project is explained implicitly as the project to steer. While not exhaustive, the description compensates for the schema gap.

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 explicitly states the tool's purpose: 'call this when next_task returns nothing (or the user asks to keep improving)'. It clearly identifies the tool as a steering mechanism that returns ordered passes. The sibling list includes next_task and next_wave, and this description uniquely distinguishes steer_project as the churn loop's answer to an empty queue.

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 guidance: 'call this when next_task returns nothing (or the user asks to keep improving)'. Also explains the four-step process (REVIEW, TIGHTEN, RESEARCH, RESUME) and includes failure handling: 'If actionable is false twice in a row, report to the user and stop'. This gives the agent clear decision criteria.

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