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

Annotations declare readOnlyHint=true, and the description adds significant behavioral details beyond that: merging live data, scoring, buffer time, timezone handling, return format (up to 8 slots with allFree/compromise). No contradiction, and the description enriches agent understanding.

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 well-structured: starts with main purpose, adds key behavioral details, ends with defaults and auth requirement. It is succinct without unnecessary 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 complex tool with 5 parameters and no output schema, the description covers scoring logic, constraints, return format, and authentication. It lacks minimal details like error behavior, but is adequate for selection and invocation.

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 100%, and the description adds extra context like default window of 14 days, timezone fallback role, and that the authenticated user should be included as host. This goes beyond the schema's basic descriptions.

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 uses a specific verb 'Rank' and specifies the resource 'meeting times for given participants', clearly distinguishing from siblings like 'suggest_time' by mentioning merging multiple data sources (calendar, manual, heat-map).

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 explicit context on when to use (finding best meeting times) and includes details like filtering Mon-Fri waking hours, scoring in timezones, buffer time, and authentication. Does not explicitly state when not to use or contrast with alternatives like 'suggest_time', but the context is clear.

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