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

Goes well beyond destructiveHint=true by naming what is destroyed (anything omitted is removed), the refusal condition (filters still tagged on prompts), and the structural limits (5 filters, 50 values). These are the operational details an agent needs before a mutation that annotations cannot express.

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?

Four tight sentences with no filler: the replacement semantics lead, followed by the refusal guard and then the numeric constraints. Every sentence contributes a distinct rule.

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 destructive, no-output-schema tool, the description covers destruction, guard rails, and format constraints well. The remaining gap is sibling disambiguation from update-prompt-filters, plus no indication of what is returned on success.

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 coverage is already 100%, but the description restates the cardinality caps (5 filters, 50 values) and the key/slug character rules in prose, which helps the agent construct a valid payload without re-reading patterns. It omits any guidance on label fields, so it is not fully additive.

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?

"Replace the custom filters a domain declares" gives a specific verb (replace) and resource (custom filters), and the full-replacement semantics distinguish it from a read tool. However, it never mentions or contrasts with the sibling update-prompt-filters, which an agent must disambiguate against on its own.

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?

Explicitly says to send the complete intended list rather than a patch, and points at list-prompt-filters as the source of the current state. It gives a clear usage context but offers no exclusion criterion versus update-prompt-filters.

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