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

Annotations already indicate destructiveHint=true, and the description adds context about replacement behavior, persistence across research re-runs, and the effect on scoring/harvesting. It doesn't contradict annotations and gives meaningful extra behavioral detail beyond the structured hints.

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?

The description is compact and well-structured: main purpose first, then examples, then behavior notes. Every sentence adds value, with no redundancy or filler.

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 tool with destructive annotations, the description covers semantics, replacement behavior, and persistence. It doesn't mention return values or errors, but given no output schema and the simplicity, this is sufficient. The only gap is explicit permissions or reversibility, but the destructiveHint covers the risk.

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 0%, so the description must compensate. It explains the 'terms' parameter thoroughly (array of strings, replacement semantics, clearing with []) and gives examples. The 'projectId' parameter is self-evident from the name and type; no additional description needed.

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 clearly states the tool sets project-level exclusion terms, with specific verb and resource, and gives concrete examples ('wedding suite', 'free template', 'printing'). It distinguishes this from other setters by focusing on exclusion terms and their effect on scoring and harvesting.

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?

Provides usage context: it replaces the whole list, can be cleared with [], and survives research re-runs unlike per-cluster dismissal. This implies when to use it over alternatives, though it doesn't explicitly say 'use this when...' or list all alternative tools.

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