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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description goes beyond them: results are privacy-preserving value-free skeletons, ranked by recent success, accompanied by observed success rate and latency, and explicitly 'currently-working' (i.e., time-sensitive). It does not say what comes back when no recipe is known or how many recipes are returned, which is the notable remaining gap given there is no output schema.

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 core purpose, then purpose-adjacent detail, then return characteristics — a sensible ordering with no filler. Slightly long for two parameters, and 'privacy-preserving — never real argument values' is a mild restatement, but each sentence still carries information.

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?

With no output schema, the description does the heavy lifting on returns (shape skeletons, success rate, latency, recency ranking) and covers the optional filter. Missing only edge-case behavior — no-recipe-found responses and result cardinality — which keeps it short of a 5 for a tool whose whole value is its returned data.

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 both parameters are already documented, and the description's 'optionally filter by a coarse task tag' largely restates the schema's task field. The only added meaning is that `toolId` tolerates loose identifiers and that returned shapes carry no real values — useful but marginal, so the baseline 3 applies.

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 and resource ('Get a CURRENTLY-WORKING call pattern (input shape) for a tool') and immediately qualifies what the artifact is: distilled from real successful calls, value-free skeletons, ranked by recent success. An agent can tell this apart from generic tool-discovery siblings 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?

Gives two concrete triggering conditions: 'when you are unsure how to shape a tool's inputs' and 'right after a tool call failed and you want a structure known to succeed now.' That is clear usage context, but it never names the obvious alternative (prepare_tool_call) or states a when-not condition, so it stops short of full alternative routing.

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