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

With no annotations provided, the description must fully disclose behavioral traits. It only states that 'The body is discarded,' implying the input is not retained, but it fails to explain the output—does it return a boolean, an error message, or something else? It also doesn't mention whether the tool makes network calls, has side effects, or handles malformed input gracefully. For a validation tool, the return behavior is critical and left entirely unexplained.

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 exceptionally short—two sentences—which is concise and front-loads the primary action. However, it is so terse that it borders on under-specification, omitting crucial details like what 'body' refers to and what the tool returns. The conciseness is a positive, but the lack of structure or elaboration prevents it from being a 4 or 5. It earns a middle score because it is efficient but incomplete.

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 the tool has 9 parameters, zero annotations, and no output schema, the description is markedly incomplete. It fails to explain the return value, which parameter is the JSON input, how the validation result is presented, and whether any parameters are ignored. An agent would need to inspect the schema for every parameter and still lack clarity on the tool's behavior. For a tool with this complexity, the description should provide significantly more context to enable correct invocation.

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 description coverage is 100%, meaning every parameter already has a description. The tool description adds no additional meaning to the parameters, leaving the schema to do all the work. For example, the 'json' parameter is described as 'JSON text to validate; discarded after the check,' which is clear in the schema. The tool description's reference to 'body' could map to 'json,' but this is not explicit. Since the schema is comprehensive, a baseline score of 3 is appropriate—no added value but no harm either.

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 clearly states the core action: 'Check whether a body is valid JSON.' This is a specific verb and resource, and it distinguishes from sibling tools like 'domain-shape' or 'file-path-ok' that check other formats. However, the term 'body' is ambiguous—none of the 9 parameters are named 'body,' so an agent cannot infer which input to supply without looking at the schema. This ambiguity slightly reduces clarity, but the overall purpose is still well-defined.

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 provides no guidance on when to use this tool versus alternatives, nor does it mention any exclusions or conditions. It does not say 'Use this when you need to validate JSON' or contrast it with similar validation tools like 'domain-shape' or 'file-path-ok.' An agent would have to infer usage purely from the tool name and schema, which is insufficient for a multi-tool environment.

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