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

No annotations are provided, so the description carries the full burden of transparency. It discloses key behavioral traits: determinism ('Deterministic, fixture-verified'), rate limiting ('free for guests...rate-limited'), the return of a 'Guild-signed provenance envelope', and a strict payload schema ('MUST match this JSON Schema'). This goes well beyond minimal disclosure.

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 front-loaded with a concise summary, then adds necessary details about usage, behavior, and parameter constraints. It includes two schemas, which are justified but make the text longer than ideal. Every sentence contributes information, so it earns a high score, though it could be tightened slightly.

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?

The description provides a complete picture for a tool with a complex payload: it defines the input parameters, the output schema, behavioral guarantees (deterministic, provenance), and usage context (alternative to model-based reading). Given the presence of an output schema, it need not describe return values further. It is self-contained and leaves no critical gaps.

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 input schema in the structured data is highly generic (payload object with additionalProperties: true, plus an api_key), offering zero description of parameters. The description fully compensates by embedding a detailed JSON Schema for the payload, specifying csv (string, maxLength 60000), delimiter (string, maxLength 1), and has_header (boolean), along with required fields. This gives the agent all necessary semantic information.

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 opens with a specific verb phrase 'Parse CSV/TSV text into JSON row objects', clearly stating the tool's function and resource. It distinguishes itself from sibling tools such as ag_table_json_to_csv, which performs the reverse operation, thereby making the purpose unambiguous.

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 explicitly positions the tool as a 'Deterministic alternative to model-based table reading', giving a clear context for when it should be used. It also mentions cost/rate limits (free for guests, pass api_key for member budget) which aids in usage decisions. However, it does not explicitly name or contrast with specific sibling tools, so it falls short of a full when-to-use/when-not-to-use guide.

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