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 does disclose two useful traits: no network calls and a cost of 1 credit per call. However, it omits failure behavior for malformed input, output format, and the 1,000,000-char input limit, which matters for a mutation-free but size-constrained tool.

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, each earning its place: purpose first, then a behavioral note, then cost. Nothing is padded or repeated.

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 tool with no annotations and no output schema, the description covers purpose, cost, and environment but never states what the tool returns (converted text vs. an object), nor how oversized or malformed input is handled. Enough to call it, not enough to predict its behavior.

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 50%: 'data' is documented in the schema while the 'direction' enum carries no description. The description's phrasing ('between CSV and JSON text') only obliquely implies the two direction values and adds no format or limit detail beyond the schema, so baseline 3 is appropriate.

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 gives a specific verb and resource ('Convert between CSV and JSON text'), and the word 'text' implicitly separates it from media-conversion siblings like convert_media and subtitle_convert. It stops short of explicitly naming any alternative tool, so it is clear but not fully sibling-differentiating.

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?

'Useful for cleaning scraped data' hints at a context of use but gives no when-to-use/when-not guidance and does not route the agent to or away from alternatives such as csv_profile or extract_tables. Usage is only implied.

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