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

With no annotations, the description carries the full behavioral burden, and it only discloses that 'values are discarded.' It does not state whether the operation is read-only, whether calling it mutates the memory implied by the tool name, what the return value is, or what happens for an empty object. For a tool whose name suggests internal state, the side-effect profile is a significant undisclosed 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?

Two terse sentences with zero fluff: purpose first, behavioral note second. Every word earns its place. It scores below 5 only because the extreme brevity leaves the tool under-specified, though that deficiency is penalized in other dimensions.

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 tool with 9 parameters, none required, no annotations, and no output schema, an 8-word description is completely inadequate. It does not explain what the tool returns, why the schema contains nine unrelated optional parameters, whether any parameter is actually required for the operation, or how this relates to similar siblings. An agent cannot reliably invoke this tool correctly based on the provided definition.

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%, which normally earns a baseline of 3, but the description actively misleads parameter understanding: it refers to a single JSON object, yet 8 of the 9 parameters (ref, url, city, feed, host, path, zone, query) are unrelated strings whose schema descriptions reference other tools. The description does not clarify that the JSON object is likely internal memory rather than the `json` parameter, creating genuine ambiguity about what the agent should pass.

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 'Count keys in a JSON object' largely restates the tool name (key-count) and adds only the vague qualifier 'in a JSON object' without specifying which object — the `json` parameter, or internal memory suggested by the tool name. It also fails to distinguish from siblings like validate-json or hn-front-count, leaving the agent unable to tell what this tool is actually for.

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 guidance on when to use this tool versus alternatives. No sibling is named, no condition is stated, and no exclusion is given, so an agent has zero basis for choosing this over validate-json or any other shape-check sibling.

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