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

With annotations present the bar is lower, and the description does add real context beyond them: per-call cost (3 MESH/call), strict output shape (answer only, one short line when blocked), and the existence of a 'blocked' outcome. However, 'blocked' is never defined (safety filter? quota? permissions?) and the non-read-only nature implied by readOnlyHint=false is not explained — only inferable from the credit charge. The 3 MESH/call quota note is the strongest added signal.

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?

Three short sentences plus a compact parenthetical cost note — front-loaded with the output contract. Minor waste: 'Quiet Query — A quiet query skill' repeats the name and title already supplied in structured fields, which delays the useful content by a few words.

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?

No output schema exists, so the description carries the return-value burden and does address it ('only the matching answer', 'one short blocked line'). But for a tool whose sole parameter is a nested capability-specific payload, it never explains how the 'data to search' is supplied or how the payload is formed, leaving the main integration question to the schema's example string.

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 single nested `input` payload and its capability-specific examples ({think:'...'}, {action:'store'|'recall'}) are already documented in the schema. The description only restates it loosely as 'a question and data to search' and adds no format or routing detail beyond that. Baseline 3 applies when the schema does the heavy lifting.

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?

It states a verb ('query') and an input shape ('a question and data to search') plus an output promise ('only the matching answer'), which is more than a tautology. But what domain or data source it queries is never said, and its distinction from siblings like `search`, `web-search-placeholder`, or `devdesk-cog-public-ask` rests entirely on output terseness rather than function. An agent can tell it is terse, but not precisely what it queries.

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?

There is no when-to-use guidance, no exclusions, and no named alternative among the many search-like siblings. The only implied condition is stylistic ('no preamble, no status chatter'), which does not tell an agent when to prefer this over `search` or `agent-brain`.

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