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

Annotations already declare destructiveHint=true, but the description adds substantial context beyond them: deletion is immediate and irreversible, requires user confirmation first, layer deletion removes the layer AND its pins, layer deletion is owner-only, and effects are scoped to the caller's own data plus admin-shared layers. These are real behavioral constraints not derivable from annotations.

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?

Front-loads the action and the immediate/irreversible warning, then walks through the modes in order. It runs a bit long, but for a multi-mode destructive tool every sentence (warning, confirmation, three modes, ownership scope) carries functional weight rather than padding.

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 what an agent needs: the safety profile, the confirmation requirement, permission boundaries, and how to address each target. Nothing required to call it correctly 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 coverage is 100%, so the schema already documents each parameter; baseline would be 3. The description adds genuine value by explaining the combination logic across parameters (scope + layerName without compIds clears pins but keeps the layer; layerId vs layerName resolution), which the individual field descriptions cover only in isolation.

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 (delete) and resource (pins/records), then enumerates the three deletion modes precisely. No sibling tool in the list performs deletion, and this description makes the destructive scope unmistakable. An agent can tell exactly what it does without opening the schema.

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 maps each mode to triggering parameters ('Use compIds to delete specific pins', 'Use scope layer with layerName...', 'Use scope comps with a layerName and no compIds...'). It also states the intent condition ('when a user wants to clear out old/junk pins or empty a layer') and adds a confirmation prerequisite.

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