log_lab_results

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

Even though annotations mark this as readOnly=false, the description adds substantial behavioral context: the required list_lab_markers workflow, the infer-not-ask policy for date/panel_name/flag/reference ranges/lab_name, and the requirement to submit all markers from one visit in a single call. No contradiction with annotations.

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 densely informative and well organized with clear sections (glucose routing, workflow, inference policy). It front-loads the purpose and gives the most critical routing distinction early. Minor redundancy exists between the workflow section and schema field descriptions, but 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?

For a lab-logging tool with nested result items and several inferable fields, this description is complete: it covers when to use it, how to prepare parameters, how to disambiguate from related tools, what to infer, and how to batch submissions. The output schema exists, so return-value details do not need to be repeated.

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 coverage is 100%, so the schema already documents each field well. The description adds extra parameter-level guidance: use canonical marker_name and loinc_code for matches, omit loinc_code when no match exists, infer defaults for several fields, and batch all markers from a visit into one results array.

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 and resource: "Log one or more blood test or biomarker results." It also distinguishes from log_wearable by explicitly routing glucose measurements to that sibling, so an agent can tell them apart.

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 explicitly says when to use this tool (lab/blood-draw results from a PDF, paper report, or photo) and when not to use it (finger-stick, CGM, home meter, wearable glucose belongs in log_wearable). It also defines a required workflow with list_lab_markers and tells the agent what to do if results are mentioned but not shared.

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