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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real value beyond that: the return shape ('matched values with their normalized paths'), batching behavior, a per-call price under x402/Solana, and an equivalent HTTPS endpoint. It stops short of stating payment setup requirements, failure/charge behavior in detail, or how the limit parameter truncates results.

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 purpose and a worked example, then return format, then transport and pricing — a sensible ordering. The feature enumeration is long but each item is informative for writing a query; only the closing HTTPS-endpoint sentence feels appended rather than integrated.

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 carries the return-value burden and does so ('matched values with their normalized paths'), and it discloses cost and transport. The remaining gap is that limit (default 1000, max 10000) and truncation behavior are never explained, which matters for large documents.

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 75%, so the baseline is already high; the description goes further by spelling out the JSONPath grammar (dot/bracket names, indexes, slices, wildcards, recursive descent, filters, function extensions) that the schema only gestures at with 'JSONPath expression starting with $'. It also clarifies the multi-query capability that maps to the queries parameter. The limit parameter is not mentioned in the description.

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 ('Query JSON with JSONPath (RFC 9535)') and enumerates the supported syntax features, so the agent knows exactly what the tool does and can distinguish it from siblings like json_diff, json_patch, or xml_xpath. The cited example expression makes the capability concrete.

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 implies the use case (extracting values from a JSON document via path expressions) and notes that several queries can be run per call, but it never states when to prefer this over siblings such as json_to_types or schema_validate, nor any exclusions or prerequisites beyond the payment note. Usage is inferable rather than guided.

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