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

With all annotations set to false, the description carries the full behavioral disclosure burden, and it does so thoroughly. It reveals that the tool uses the active context unless overridden, that a shot can land on the wrong bean bag without an explicit bean_id, that the diagnosis engine reads tags and metrics rather than flavor_notes, and that a tag-less/rating-less shot is filed as taste-pending. These are meaningful behaviors beyond what the annotations or schema express.

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 dense but every sentence earns its place: purpose first, then active-context overrides, backdating, taste tagging, and the clean-shot indicator. It uses emphasis and examples effectively without filler or repetition.

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 31-parameter tool with nested objects and seven enums, the description covers the most consequential behaviors: active-context resolution, overrides, taste workflow, backdating, and a pointer to diagnose_shot. The large number of optional parameters is acceptable because the schema already documents 65% of them and the output schema exists, so the description does not need to explain every field.

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?

At 65% schema coverage, the description adds important semantics to high-risk parameters: bean_id (always pass when a specific coffee is named), pulled_at (backdating and the diagnose_shot implication), sensory_tags (read by the diagnosis engine), and tasted (the explicit marker for a clean shot). It does not enrich every optional parameter, but it targets the ones that most affect correctness.

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 and resource: 'Log an espresso or alternative shot/brew attempt.' This clearly distinguishes the tool from sibling tools like update_shot, delete_shot, and diagnose_shot, so an agent knows exactly what action this call performs.

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 gives concrete conditional guidance: pass bean_id explicitly when the user names a coffee, use pulled_at when backdating, add sensory_tags for taste reports, and set tasted=1 for clean shots. It even points to diagnose_shot for backdated entries. It does not explicitly list when to avoid this tool in favor of update_shot or delete_shot, but the creation context is otherwise clear.

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