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

Annotations only declare hints (write, not destructive, not idempotent, not open-world); the description adds a genuine privacy disclosure — no personal data stored beyond the account id when signed in — plus the user-facing follow-up obligation. It does not explain what becomes of the record (who sees it, whether duplicates are deduped given idempotentHint=false), leaving a modest 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?

Front-loaded with the trigger condition, then enum semantics, then privacy, then follow-up — logical order with no filler. The middle sentences are densely packed run-ons that take a careful read, which costs it a point.

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?

An output schema exists, so return values need no explanation. Combined with 75% schema coverage, the description supplies everything missing: when to fire, how to classify, what to include, privacy implications, and required follow-up with the user.

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 enum lists the four `kind` values without describing any of them; the description supplies the precise meaning and selection rule for each. It also guides `need` ('one short sentence') and `tool` ('name the tool when one fell short'), though `context` is left entirely to 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 names a specific action (record a gap) and a specific condition (the user needed something kernelCAD does not have), which no sibling tool shares. It also distinguishes the tool from silently working around the gap ('recorded instead of papered over'). An agent can identify it 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 enumerates four gap categories (asset, capability, output, docs) with the exact triggering condition for each, including naming the failing tool when relevant. It also closes the loop with 'Then tell the user plainly what is missing,' which is an instruction about what to do after calling.

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