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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real context beyond them: bounded depth and key counts, and that input is neither executed nor persisted. It stops short of saying what happens on invalid input (error vs. false result), which matters for a validator with 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?

Three short sentences, front-loaded with purpose and routing, with no filler. The opening clause 'Parse JSON using upstream safety limits' slightly overlaps the later 'Checks JSON syntax with bounded depth and key counts', a small redundancy rather than a flaw.

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 one-parameter, annotation-rich, output-schema-less validator, the description supplies the needed scope and non-mutation guarantees. The remaining gaps are the concrete limit values and the return shape on failure, both minor for a self-describing safety check.

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% and the single parameter already documents the 4096-character cap and the depth/key-count limits, so the description's mention of 'bounded depth and key counts' largely restates the schema. 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?

States a specific verb and resource ('Parse JSON ... test whether text is valid JSON') plus the scope of the check ('within depth/key constraints'). It also names the sibling it is not ('For CSV/JSONL cleanup, use is-dataset-minify instead'), so an agent can separate it from the other is-* validators without opening a 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 an explicit trigger ('Use to test whether text is valid JSON within depth/key constraints') and an explicit redirect to an alternative with the condition that selects it ('For CSV/JSONL cleanup, use is-dataset-minify instead'). This mirrors the pattern of the strongest calibration example.

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