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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, covering the safety profile. The description adds real value beyond that by describing the response content (the prompt, conclusion, and rationale), which is more than the annotations convey.

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 short sentences, front-loaded with the core action and followed by the motivating use case and a doc link. Every sentence earns its place, though the doc-link sentence is marginal rather than essential.

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 simple two-parameter read tool with full annotation coverage, an output schema, and 100% parameter documentation, the description is complete: an agent knows what it does, when to call it, and what it retrieves. Nothing needed for correct invocation 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 description coverage is 100%, with both limit and monitor_id fully documented including defaults and bounds. The description adds no parameter-level detail, so the schema does the heavy lifting and 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?

States a specific verb and resource ('Get the results of the AI check on a monitor') and then enumerates the content returned (what the AI verified, concluded, and why). No sibling tool covers AI checks, so it is unambiguously distinguishable from the surrounding get_* 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?

'Use this to see why an AI monitor passed or failed' gives a clear selecting condition for the tool. It does not name an alternative or any exclusion, but for a uniquely-scoped read tool the usage context is well established.

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