get_preferences

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

With no annotations, the description carries the behavioral burden and does so well: it warns that unusable_equipment must never be used in planning, defines ★preferred vs ⊘avoided notation, and specifies that legacy injury facts should be treated as hard constraints until curated. It does not cover pagination or freshness of the data, but the interpretation guidance is substantial.

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 identifying phrase 'The coaching memory:' and every clause conveys distinct content about the returned structure. It is a single dense run-on enumeration rather than grouped prose, which slightly hurts scannability, but no sentence is wasted.

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 describe return values itself — and it does so exhaustively, enumerating each fact group (constraints, preferences, goals, observations, conflicts, legacy buckets). Nothing an agent needs in order to interpret the response is missing.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. Schema description coverage is 100% and the empty arguments object leaves no semantic gaps.

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 the resource ('the coaching memory') and enumerates exactly what it holds (goal, training days, session length, load anchors, equipment, preferred/avoided exercises, curated facts). It is clear what data the tool returns, though it never uses an explicit retrieval verb, and it does not distinguish itself from siblings like list_facts or set_preferences.

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 concrete workflow guidance: 'Check facts.constraints.hard before building any workout; resolve any conflicts with the user,' and instructs curating legacyToReview promptly. It does not name alternative tools or state when not to call it, so it stops short of full when/when-not routing.

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