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

The description adds substantial context beyond the sparse annotations: it names the serving model ('Runs claude-haiku-4.5'), states the cost ('5 MESH/call'), notes that the response names the model, and details the return structure. It also characterizes the tool as 'reasoning'. No contradiction with annotations; readOnlyHint=false is not contradicted by the output-producing behavior.

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 a single sentence but packed with essential information: purpose, output format, model, cost, and I/O shape. It uses em-dashes and parentheticals efficiently, with the core purpose leading. Every clause earns its place, and there is no redundant or filler content.

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?

With no output schema present, the description fulfills that responsibility by listing the returned fields: {analysis: {summary, steps, risks, verdict}, model}. It also covers cost, model, and input shape, providing enough context for an agent to invoke correctly. The detailed schema complements the description, making the tool well-specified for its complexity.

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?

The tool description only restates 'Input: {task: string}' while the input schema's description is far more detailed, covering coercion, trimming, truncation to 4000 chars, whitespace rejection, and fallback keys. Since schema coverage is 100% and the schema already provides rich parameter semantics, the description adds no extra meaning beyond a basic restatement. Baseline 3 is appropriate.

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 clearly states the tool's function: 'Hand a task, get a structured plan back — typed steps, risks, and a go/caution/no-go verdict.' It also specifies the output structure and the model, making the purpose specific and unambiguous. While it doesn't explicitly distance itself from sibling tools like 'task-orchestrate', the unique output type (steps, risks, verdict) distinguishes it.

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 implies usage context ('Hand a task, get a structured plan back') but provides no explicit 'when to use' or 'when not to use' statements. It does not mention alternative tools or exclusions for scenarios where another tool would be more appropriate. This is implied guidance at best, not explicit alternative naming.

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