fitbit_trends

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

With no annotations, the description discloses auto-syncing behavior and detailed return values per data_type. It reveals what the tool does beyond the schema: computing averages/totals, and lists specific metrics for each type. No contradictions.

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 moderately sized but well-structured with an args list and returns section. It front-loads the purpose and packs useful detail without redundancy. Could be slightly more concise, but earns its length.

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?

Given 5 parameters, no required params, and an output schema, the description fully covers parameter usage, return values per data_type, and behavior. Everything an agent needs to correctly invoke and interpret the tool is present.

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 0%, but the description thoroughly explains each parameter: allowed values for data_type and period, date format examples, and compare syntax with defaults. This adds substantial meaning beyond the 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 it analyzes trends in cached Fitbit data and distinguishes from raw data tools: 'Not for raw data - use fitbit_get_* tools instead.' The verb 'analyse' and resource 'trends in cached Fitbit data' are specific and differentiate it from sibling tools.

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 explains auto-syncing if stale, and clarifies that when 'compare' is set, period/start_date/end_date are ignored. It also tells when not to use: for raw data, use fitbit_get_* tools. However, it doesn't compare with other potential trend tools (none exist), so it's clear but not explicit about alternatives.

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