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

Annotations cover only the read-only safety profile, and the description adds a lot beyond that: newest-first ordering, per-line structure (kg×reps, s/m for timed/distance, bw, sets done/planned, RPE vs target), the days-since-previous marker, header frequency stats, and the 14-day BREAK rule that reframes the next load as a return rather than a step up. This is exactly the extra context the annotations do not provide.

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 what the tool returns, but it degenerates into a run-on paragraph mixing return format, coaching heuristics ('one axis moved and named; over target or unfinished = the same load'), and prose like 'Arithmetic over the log, nothing to cite.' It is dense and hard to scan, and the house-practice sentences are arguably guidance rather than tool semantics.

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?

There is no output schema, so the description must carry the return format itself, and it does: per-exercise lines, their fields, the header aggregate, and the BREAK annotation. An agent can predict the shape and interpret the numbers without a schema.

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 100%, so the baseline is 3, but the description adds real meaning to `exercise`: it is a substring match against the athlete's own names, with a concrete example ('присед' finds both squats), which the schema only partly conveys. The sessions cap and 4/12-week windows are mentioned, though the default of 8 sessions is left to 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?

States a specific verb and resource: the per-exercise lift history across sessions, with ordering (newest first). It also differentiates itself from a near-sibling by noting 'the snapshot's strength_progression has the last three for exercises in view; this has a year', so the agent can tell it apart from the other progression 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?

Gives explicit usage: 'A WEIGHT COMES FROM HERE: read it before writing a kg' and, for ambiguous exercise names, 'ask, then link_exercises', which routes to a specific sibling. It does not, however, explain when to choose get_strength_log or get_progression instead, so the alternative routing is only partial.

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