read_records

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuinely non-obvious behavioral context: weights are reported in the profile unit, and a dumbbell exercise is interpreted under its current weightMeans convention (each vs total). That data-semantics disclosure goes well beyond what the annotations supply.

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?

It is front-loaded with the returned content before moving to sorting, and every sentence carries information about either output fields or parameter interpretation. The dumbbell parenthetical is dense but load-bearing, so the size is justified even if not maximally tight.

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 no output schema, the description carries the burden of describing returns and does so by enumerating the per-exercise fields, plus unit and formula semantics. Minor gaps remain (no explicit note on how 'since' filtering interacts with the record definition, and truncation is only mentioned in the schema's limit description), but an agent can call this correctly.

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 75%, so fields like limit and since are already documented, but the description adds real meaning for the formula parameter (single formula gives no estimate above 12 reps; weighted blends all seven and counts reps in reserve up to 15; 1 rep equals the weight itself) and confirms the default resolution order. That is meaningful interpretation beyond the enum list.

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 resource and enumerates exactly what a 'record' contains (best weight and when, best estimated 1RM and its source set, session count, last done), so an agent knows this is a per-exercise personal-records read rather than a raw history listing. It does not explicitly contrast itself with the near-neighbour read_exercise_history, which is the only thing keeping it from a 5.

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 states the default sort and the sort options, which implies how to use it, but never says when to reach for read_records versus read_exercise_history or read_exercises. No exclusions or prerequisites are given, so usage context is inferred rather than stated.

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