Run sentinel cycle (agent loop)

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

The description fully discloses the mutation behavior: it 'act[s] by setting status to needs_attention and recording a recommended action'. It also explains the decision triggers (deadline close, high risk, never reviewed) and mentions rendering the widget. Annotations are consistent (readOnlyHint false, destructiveHint false), and the description adds context beyond annotations, such as the specific recorded actions and evidence gathering.

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?

Three sentences, each earning its place: first describes the core loop, second provides scheduling/usage context, third mentions the UI output. No filler or repetition; front-loaded with the primary action.

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 tool with a moderately complex loop, two optional parameters, and no output schema, the description covers the full workflow, side effects, intended usage, and a key UI outcome. It does not need to explain return values since no output schema exists, and the schema covers parameters. Very 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 description coverage is 100%, so the schema already documents both parameters (dryRun and onlyContractId) with clear descriptions. The description does not add parameter-specific meaning, but baseline 3 is appropriate since the schema carries the semantic load. No gap to compensate.

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 names a specific verb ('Run the autonomous Contract Sentinel agent loop') and resource ('entire tracked portfolio'), and details the workflow (perceive, score, decide, act). This clearly distinguishes it from sibling tools like review-portfolio (which likely only reviews) and ingest-contract (which likely ingests).

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 states it is 'designed to run on a schedule in production; runnable on demand here', giving clear context for when to use it. It does not explicitly name alternatives or exclusions, but the 'entire tracked portfolio' scope and 'on demand' note imply usage patterns. A brief mention of when not to use (e.g., prefer review-portfolio for quick review) would make it 5.

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