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

Adds real value beyond the annotations (which already declare readOnly/idempotent/non-destructive): completeness (no monitors omitted), per-monitor cost (~140 tokens), and the semantics of the count categories. The ordering claim ('the order they come back') is left vague rather than named (creation date, name, etc.), the one real gap.

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 labeled lines (Purpose/When/Cost) front-load scope, then selection guidance, then a budget. Every sentence carries information an agent needs; nothing repeats the schema or annotations.

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 an output schema present, return values needn't be documented, yet the description still explains the count buckets and the cost — enough to call this confidently with no arguments. Only the unspecified sort order keeps it from being fully 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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly implies no inputs are needed and instead spends its words on the return shape.

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 ('List every one of the user's saved monitors') plus a scope guarantee ('none are left out') and what each row contains (counts). This implicitly separates it from monitor_get (single monitor), though no sibling is named outright, keeping it just short of a 5.

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?

'When: Before choosing or changing a saved monitor, to find the one the user means' gives a clear triggering condition and implies the follow-on tools (monitor_get, monitor_update, monitor_decide). No explicit when-not or negative case is stated, so it falls short of a 5.

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