build_lens

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

With no annotations, the description carries the full behavioral burden. It does disclose the write destination and that output is 'personal, not shipped', plus the interactivity requirement — real behavioral context. But it omits overwrite/idempotency behavior, whether existing lenses are destroyed, and any permission or rate-limit constraints.

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?

Dense and front-loaded: purpose first, then source options, kind, output, and workflow. Uses arrows and private notation (P1/U1, rule #8) that is cryptic but compact; nearly every clause carries information.

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 12-parameter tool with no annotations and no output schema, the description covers the core concept, source modes, kind, destination, and interactive requirement. It is, however, incomplete on the many undocumented parameters and on behavioral traits, leaving gaps an agent must guess at.

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 0%, so the description must document all 12 parameters, yet it only explains ground_text/ground_url/ground_path, kind's enum values, and reading_notes. axis, dest, name, slug, author, license, and run_kernels are left undocumented, so a majority of parameters carry no semantics anywhere.

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?

States a specific verb+resource: 'build a grounded-LENS from any source', and distinguishes the concept from personalities ('lenses > personalities'). It also explains the P1/U1 layering, so an agent understands what artifact is produced. It stops short of naming a sibling tool it should be chosen over.

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?

Gives concrete workflow guidance: the result lands in advisors/<slug> and should 'immediately' be used with cite/retrieve, and it flags that assembly is interactive (ask for source + 'how YOU read'). No explicit when-not-to-use or sibling alternative is given, so it is context without exclusions.

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