invariance_monitor_evaluate

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

Annotations already indicate non-read-only and non-destructive behavior, and the description reinforces the side-effect profile by saying the evaluation returns 'the resulting execution plus any signals/findings/reviews produced.' This tells an agent that the call can create evaluation artifacts, not just read data. It does not mention cost/time or permissions, but the core mutation behavior is clear.

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?

A single sentence puts the action and scope first, with the return payload in a parenthetical. There is no filler and no redundant repetition of schema 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?

With no output schema, the description usefully summarizes the return payload (execution plus signals/findings/reviews), and input semantics are mostly delegated to the schema. It is sufficient for a simple two-parameter tool, though the implicit `id` and lack of explicit alternative routing leave small completeness gaps.

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 `input` parameter is well-specified in the schema with field meanings, types, and an example, so the description only needs to echo the concept of scope. However, the required `id` parameter has no description in the schema and is only implicitly a monitor identifier from the tool description. This is the main semantic 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 names a specific action ('Manually evaluate'), a resource ('a monitor'), a timing/trigger ('right now'), and a scope qualifier ('explicit input scope'). It also states what is returned, making it easy to distinguish from monitor_executions or preview-oriented sibling tools.

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 phrase 'Manually evaluate a monitor right now' provides clear context for on-demand use, and 'against an explicit input scope' signals when a scoped, one-off evaluation is appropriate. It does not explicitly name sibling alternatives or state when not to use them, so it stops short of a full routing guide.

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