Apply Lens

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

With no annotations provided, the description carries the full transparency burden. It discloses critical behavioral traits: the 'analysis' parameter is narrative, 'findings' must be nested as a JSON object, and the response includes prior findings from earlier lenses (stateful behavior). It also notes ordering constraints ('Allowed after synthesize') and that it can be called multiple times, all beyond what the schema conveys.

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 long but well-structured, with important usage notes and examples front-loaded. Every section adds value: purpose, critical parameter instructions, example, model reference, and usage lifecycle guidance. The exhaustive model list is arguably necessary for selection, but it does add bulk, preventing a perfect score.

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 tool with no output schema and complex nesting requirements, the description covers all essential aspects: how to structure calls, what parameters mean, which models are available, and how the tool fits into the session flow. The only gap is an explicit description of the response format beyond the note that it includes prior findings, but overall completeness is high.

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?

Although schema coverage is 100%, the description adds significant meaning beyond the structured definitions. It clarifies the distinction between 'analysis' and 'findings', explains that findings keys must match the model's required field names, and provides a full example call. The extensive model list in the description also expands on the generic 'Model to apply' schema hint, making parameter selection much easier.

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+resource: 'Apply a systems thinking model to the current problem.' It clearly distinguishes from siblings by noting it applies one lens, while 'synthesize' is for integrating across lenses. The tool's role in the session lifecycle ('Can be called multiple times per session. Allowed after synthesize.') further clarifies its placement.

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?

Explicit guidance is provided on when to use the tool ('Apply 2-4 lenses per session') and when to use an alternative ('When you've built enough perspective, call synthesize to integrate across lenses'). The description also tells users not to stop after one lens and warns against passing findings as top-level parameters, offering a concrete example call structure.

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