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

With only generic annotations available, the description carries the full behavioral burden and does so well. It discloses that nothing is published, that Gate 1 validation runs immediately with results returned, that human approval is required, and that no autonomous process publishes a Record. This goes well beyond the annotation hints and does not contradict them.

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 key caveat about creating a request rather than a Record is front-loaded, which is good. However, the description is verbose: the slogan line 'Mirror measures, the Record responds' adds little functional value, and 'No autonomous process publishes...' largely restates the earlier human-review point. Not every sentence earns its place.

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?

Given that there is no output schema and the tool has 19 parameters, the description provides a surprisingly complete workflow picture: request creation, immediate Gate 1 validation, returned results, human review, organizational approval, and version reporting. It does not describe the exact response structure, but for a request-submission tool this is a minor gap.

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 description coverage is 100%, with detailed field-level descriptions such as 'At least 3 authoritative sources from 3 DIFFERENT domains' and 'E.164 format, e.g. +1-802-760-4653.' The tool description adds only a general requirement to provide 'verified, citable facts only,' so the schema carries the parameter-documentation load and the description does not need to compensate.

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 states a specific verb and resource: it requests a Brand Discovery Record. It also draws a crucial distinction between creating a REQUEST and creating a Record, and differentiates itself from the human-delivered 'full Brand Reflection.' An agent can tell exactly what this tool does.

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?

There are no sibling tools, but the description gives clear operational context: this is the one public tool, calling it creates a request, Gate 1 validation runs immediately, and results are returned. It does not explicitly state when not to use it, but the request-vs-record caveat and the human-delivered measurement boundary serve as practical guidance.

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