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

Annotations already indicate read-only and non-destructive behavior. Description adds important behavioral requirements: explicit consent, rejection of PHI, preservation of uncertainty, and prohibition on inventing dates/diagnoses. This goes beyond structured annotations and gives the agent operational guardrails.

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?

Two succinct sentences convey the core action and key prohibitions. No wasted words; essential information is front-loaded.

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 an output schema and read-only annotations, the description sufficiently covers input requirements, safety constraints, and purpose. It does not need to describe return values due to output schema. The description is complete enough to guide selection and invocation among sibling tools.

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?

The description adds meaning to the observations parameter by clarifying they are user-authored and non-identifying, and to consentConfirmed by insisting on explicit consent. Schema coverage is moderate (50%), and the description compensates by setting context, though it doesn't detail individual fields beyond schema.

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 clearly states the tool's function: sorting user-authored observations into a chronological timeline while preserving uncertainty. It distinguishes itself from sibling tools (e.g., find_symptom_words, render_appointment_brief) by focusing on chronological organization rather than searching or rendering. Includes constraints like 'non-identifying' and 'no PHI'.

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?

Provides clear context for use: after explicit consent and with non-identifying user-authored observations. Mentions exclusions (do not accept PHI, do not invent dates/diagnoses). However, it does not explicitly name alternative tools or state when not to use this tool, so slightly below the highest bar.

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