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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds meaningful beyond-annotation context by disclosing that no network call is made and that each invocation is billed, both of which affect agent decisions.

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?

A single efficient sentence front-loads the core behavior ('pure-compute data conversion'), then enumerates operations and closes with the billing caveat. No filler or redundant restatement.

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 two-parameter, no-network conversion tool with no output schema, the description plus input schema provides the operations, input type, cost expectation, and safety profile. It is slightly thin on what exact output form each op returns, but the operation names make that inferable.

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%: op and data are fully described in the schema. The description restates the op values and payload types but adds no new parameter-level semantics such as format edge cases or op-specific constraints, so it earns the baseline rather than exceeding it.

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 names a specific resource (data conversion) and enumerates six exact operations (json_pretty, json_minify, json_to_csv, csv_to_json, base64_encode, base64_decode), making the tool's scope unambiguous. It also distinguishes itself from the paid_* sibling tools by narrowing to pure conversion rather than answering, hashing, summarization, or translation.

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 phrase 'pure-compute data conversion (no network)' and the operation list give clear context for when to use this tool: whenever the agent needs one of these deterministic local conversions. It does not explicitly name alternative tools or exclusion cases, so it falls short of fully explicit routing guidance.

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