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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful non-schema context: the graphs come from the user's own records, several metrics are fixed to a 30- or 90-day window, and training volume is flagged as the most salient number. It still says nothing about whether a graph is returned as an image/reference or what happens when records are sparse for the requested metric.

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?

Front-loaded with the trigger condition, then the metric catalogue, then the exclusion — a logical order for an agent scanning for a routing decision. The single editorial aside about training volume being the number that matters most is short and plausibly useful for choosing a metric, so it 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?

With an output schema present the description needn't explain return values, and it covers the metric catalogue, the key linkage, and one important scope exclusion. The remaining gap is the absence of any statement about data availability or empty-result behavior when the user has no records for the chosen metric.

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 67%, and the description meaningfully reinforces it by mapping the `key` parameter to the per-exercise graphs ("per session for one exercise (key)") and by attaching time windows to the metric options. The enum values themselves and the `note` parameter are not explained beyond what the schema already carries, so this is a modest lift over the structured fields rather than a full compensation.

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 names a specific verb and resource ("Draws one of their Progress graphs from their records") and enumerates the exact metric families it can render, so an agent can tell it apart from logging tools like log_set or get_nutrition. It falls short of naming the closest sibling, get_progress, so the boundary between the textual progress tool and this graph tool is left implicit.

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?

It gives an explicit trigger ("Use this when the person asks to see their progress on a graph") and an explicit exclusion ("Do not use for sleep or heart-rate numbers, which stay in the Almost Fire app"). What it does not do is point at the alternative tool to use instead when the request is non-graphical, which would have made routing fully unambiguous.

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