vts_discover

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

With no annotations, the description carries the full burden. It clearly labels the operation as 'local, read-only' and describes the scan and reporting behavior. It also discloses the side effect of the 'learn' parameter (feeding files into warm-set query-history). However, it does not detail permissions, rate limits, or output structure, but the core behavioral traits are covered.

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 extremely concise at two sentences. The first sentence front-loads the primary action and purpose, and the second sentence provides a usage directive. No filler words; every sentence earns its place.

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?

Given no output schema, the description states the output (raw tokens spent as missed savings) sufficiently. Parameters are fully documented in the schema. The sibling context shows it fits into the vts family. Minor gap: does not explicitly state whether it returns a list or a summary, but the purpose is clear enough for an agent to infer expected output.

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 baseline is 3. The description does not add significant meaning beyond the schema descriptions for parameters. It provides context that the scan is 'local, read-only' and about 'bypassed vts searches', which slightly enriches understanding but does not compensate beyond baseline. Schema descriptions are adequate.

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 uses specific verbs ('Scan', 'report') and a clear resource ('Claude Code transcripts' for bypassed vts searches). It explicitly states the goal: find token-heavy searches that slipped past vts and report their wasted tokens. This clearly distinguishes it from siblings like vts_savings (reports total savings) and vts_warmup (warms up cache).

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?

The description ends with 'Use to see where token-heavy text search is still slipping past vts,' providing clear guidance on when to invoke the tool. While it does not explicitly list alternatives or when-not-to-use, the sibling context implies that other tools handle reporting or warmup. The guidance is clear enough for an agent to decide.

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