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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a read-only operation confined to known results. The description's value beyond annotations is modest but real: it specifies 'the caller's monitors' (ownership scope) and the optional status filter, which are behavioral details not carried by the annotation fields. Since annotations capture the read-only safety profile, the description's additional context earns a solid 4 rather than a 3.

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 that front-loads the verb and resource, then appends the optional filter. There is no filler or repetition of schema content. It is appropriately sized for a straightforward list tool.

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 list operation with readOnlyHint=true and a clear scope, the description plus annotations provide a good picture. The absence of an output schema and the lack of detail about pagination or response shape are minor gaps given the tool's simplicity. It would be slightly stronger if it mentioned whether the results are ordered or what happens when the status filter is omitted, but those are not critical for an agent to invoke the tool correctly.

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 schema's description coverage is 75% with the status parameter having no description, and the description adds the meaning of the status filter. The context, llm_model, and conversation_id parameters are already well described in the schema. The description does not explain, for example, what the returned data looks like or whether status values are mutually exclusive, but the core parameter semantics are mostly handled by the schema.

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 'List the caller's monitors, optionally filtered by status' uses a clear verb (List) and resource (the caller's monitors), and the optional status filter is mentioned. It is not entirely trivial, since the schema doesn't include a description for the status property, so the description contributes the key filtering behavior. However, it doesn't explicitly differentiate among the sibling monitors_* tools (checks_list, events_list, get, etc.), though the domain word 'monitors' and 'list' are reasonably clear.

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 that the tool is for listing monitors and optionally filtering by status, which is useful context for choosing it over monitors_get or monitors_checks_list. It doesn't explicitly mention alternatives or when-not-to-use it, nor does it clarify the relationship to siblings like monitors_checks_list (which would also be a list of something monitor-related). It is not misleading, but it leaves the selection reasoning mostly to inference from sibling names.

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