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

With no annotations, the description carries the full burden and excels: it discloses that first occurrence is kept, order is preserved, equality is JCS-canonical, and it reports what was removed and why. It also mentions determinism, guest rate limits, the option to use a member budget via api_key, and the Guild-signed provenance envelope—all beyond basic expectations.

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 moderately long but well-structured: a clear opening purpose, followed by behavior details, and then the required schema as a code block. Every prose sentence earns its place, and the embedded schema is necessary because it is not elsewhere in the input schema. It is slightly dense but appropriate for the tool's complexity.

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 covers operation, parameter constraints, output, operational context (rate limits, api_key), and provenance. The output schema is present in the description, so return values are clear. No major gaps are apparent, especially given the lack of annotations and the tool's complexity.

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 only specifies 'api_key' and an opaque 'payload' object with 0% coverage. The description compensates by embedding a full JSON Schema for 'payload', detailing required 'records' and optional 'keys' and 'case_insensitive'. It also explains that api_key is optional for guests but can be used for member budget, adding crucial meaning.

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 clear, specific verb+resource: 'Deduplicate JSON records exactly, optionally by key subset.' This distinguishes it from siblings like ag_json_canonicalize (which canonicalizes rather than removes duplicates) and ag_data_record_link (which links records).

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 usage context through the 'optionally by key subset' and 'case-insensitive' options, but it does not explicitly state when to use this tool vs alternatives or when not to use it. No comparison to sibling tools like ag_data_record_link is provided, so guidance is only implied.

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