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

Annotations cover only readOnlyHint/openWorldHint, and the description adds meaningful behavior beyond that: an unknown topic returns the full topic index with one-line rules, so calling once with any word is a valid discovery strategy. It also prescribes output voice and formatting (cite evidence by author and year, answer in the user's language, convert kg to the user's units), which materially shapes correct use.

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 purpose, then usage, then parameter guidance, so an agent can stop reading early. The long enumeration of trigger topics is functional but makes the middle paragraph dense; a tighter grouping would lose little.

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 a single required string parameter, an output schema, and full schema coverage, the description supplies everything else an agent needs: the trigger condition, the topic-key convention, the unknown-key fallback, and the answering style. Nothing needed for correct invocation or downstream phrasing 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?

Schema coverage is 100% with one parameter, so the baseline is 3, but the description adds value beyond the schema: a second example key ('when_weight_goes_up') and, critically, the semantics of an unrecognized value (returns the topic index rather than erroring). That fallback behavior is not derivable from the schema alone.

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 ('Get the evidence card behind one of Povver's training rules') and enumerates exactly what the card contains: the rule, the research-backed why, the user-facing meaning, and sources. This is clearly distinct from siblings like get_recommendations or get_training_insights, which surface computed data rather than the rationale behind a rule.

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 an explicit trigger ('Call it BEFORE answering any question about why Povver does something') and then enumerates the concrete question classes that route here (set counting, warm-ups, 1RM/effort targets, weight/reps progression, step sizes, deloads, variations, drop sets). It also states the when-not: answer from the card, not from general training knowledge, even where literature disagrees.

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